We analyze the learned input-output behavior of GLU-based neurons in large language models (LLMs). We propose a simple analysis method: For each neuron, we compute the cosine similarities between its input (reading) and output (writing) weight vectors. In this scheme, a strong negative cosine similarity indicates the neuron weakens the direction it detects in the residual stream, so we call this a weakening neuron. This allows us to gain a number of novel insights. First, we show that nine different LLMs have similar patterns: weakening neurons appear mostly in late layers whereas their counterparts, (conditional) strengthening neurons, are frequent in early-middle layers. Second, we find that weakening neurons display surprising behavior: even though there are few, they activate often and have a large influence on model behavior. Third, weakening neurons have a strong effect on model output when gate values are negative – which is surprising since negative gate values are not expected to encode functionality.

Hallucination is a central failure mode of language models (LMs). We focus on hallucinations in response to questions like: “Which instrument did Glenn Gould play?”, but we ask these questions for synthetic entities designed to be unknown to the model. We find that LMs like Gemma-7B-IT frequently hallucinate, i.e., they have difficulty recognizing that the hallucinated fact is not part of their knowledge. Based on the idea of linear relational embeddings, we put forward the following hypothesis. (i) Due to the abstract scheme that is used to represent them, LMs can easily produce plausible objects for non-existing subjects of linear relations, which can lead to hallucinations. (ii) For nonlinear relations, this mechanism for producing an object is not available and so a hallucination is easier to avoid. To test this hypothesis, we create SyntHal, a synthetic unknown-entity benchmark for 15 relations. We find that across four instruction-tuned models, relational linearity is a strong predictor of models hallucinating an object for an unknown subject vs refusing to give an answer, with correlations r ∈ [.58, .84]$. While this is not direct evidence for the hypothesized causal mechanism, it is suggestive and opens up a new line of inquiry into understanding LM hallucinations.

The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks responsible for specific task behaviors. In this work, we investigate whether ensembling two or more circuit localization methods can improve performance. We explore two variants: parallel and sequential ensembling. In parallel ensembling, we combine attribution scores assigned to each edge by different methods—e.g., by averaging or taking the minimum or maximum value. In the sequential ensemble, we use edge attribution scores obtained via EAP-IG as a warm start for a more expensive but more precise circuit identification method, namely edge pruning. We observe that both approaches yield notable gains on the benchmark metrics, leading to a more precise circuit identification approach. Finally, we find that taking a parallel ensemble over various methods, including the sequential ensemble, achieves the best results. We evaluate our approach in the BlackboxNLP 2025 MIB Shared Task, comparing ensemble scores to official baselines across multiple model–task combinations.