2025
Enhancing Chain-of-Thought Reasoning via Neuron Activation Differential Analysis
EMNLP 2025
Despite the impressive chain-of-thought(CoT) reasoning ability of large language models (LLMs), its underlying mechanisms remains unclear. In this paper, we explore the inner workings of LLM’s CoT ability via the lens of neurons in the feed-forward layers. We propose an efficient method to identify