AI RESEARCH
Neuron-Guided Interpretation of Code LLMs: Where, Why, and How?
arXiv CS.AI
•
ArXi:2512.19980v2 Announce Type: replace-cross Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for source code due to programming languages formal, hierarchical, and executable nature. We empirically investigate code LLMs at the neuron level, localizing language-specific neurons (selectively responsive to one language) and concept layers (feed-forward layers encoding language-agnostic code representations.