Skip to content
conftrace_

activation analysis

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network interpretability (3) large language model (2) convolutional neural network (2) representation learning (2) poisoning attack detection (1) knowledge database security (1) circuit localization (1) causal variable localization (1) reasoning neuron (1) activation probing (1)

Papers

Demystifying optimized prompts in language models EMNLP 2025 Enhancing Chain-of-Thought Reasoning via Neuron Activation Differential Analysis EMNLP 2025 Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models EMNLP 2025 Neurons to Words: A Novel Method for Automated Neural Network Interpretability and Alignment AAAI 2025 RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis EMNLP 2025 Interpreting Learned Feedback Patterns in Large Language Models NeurIPS 2024 Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features NeurIPS 2024 Experimental Observations of the Topology of Convolutional Neural Network Activations AAAI 2023