Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    chat

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    糠
    0.50
    ascular
    0.48
    GlobalSection
    0.48
     Redistribution
    0.47
     Petroleum
    0.47
    ✠
    0.47
    염
    0.47
    _{*}
    0.46
     乳
    0.46
    ploidy
    0.46
    POSITIVE LOGITS
     chat
    3.52
    Chat
    3.22
     Chat
    3.22
    chat
    3.11
     chats
    3.03
     chatbot
    3.03
    聊天
    3.03
     chatting
    2.97
     chatbots
    2.81
     चैट
    2.78
    Act Density 1.956%

    No Known Activations