neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻譯準備中
Bio-inspired cognitive architecture for LLM agents providing embodied sensation, homeostatic drives, and brain-modeled persistent memory enable cross-session and cross-context learning without fine-tuning. Works with robots like the Reachy Mini or headless.
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Bio-inspired cognitive harness for LLM agents — embodied sensation, homeostatic drives, and brain-modeled persistent memory let LLM-driven agents carry learning across sessions without fine-tuning.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
Bio-inspired cognitive harness for LLM agents — embodied sensation, homeostatic drives, and brain-modeled persistent memory let LLM-driven agents carry learning across sessions without fine-tuning.檢視完整 README ↗