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

    Neuronpedia

    INDEX
    Explanations

    chat and conversation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मन
    0.44
    FEATURES
    0.39
     Vitt
    0.39
    Fundamental
    0.36
    مع
    0.35
    배
    0.34
    মন
    0.34
    #!
    0.34
    학교
    0.34
    VIEWS
    0.34
    POSITIVE LOGITS
     chat
    0.61
    chat
    0.47
     chatting
    0.47
    chatID
    0.47
     Chat
    0.44
    chats
    0.44
     chatt
    0.43
     chatId
    0.43
     chats
    0.42
    chatbot
    0.41
    Act Density 0.000%

    No Known Activations