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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries about personal experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    stories about people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.44
    WebServlet
    -0.44
    }$​
    -0.42
    Класс
    -0.41
     Audiodateien
    -0.40
    numerusform
    -0.39
     monitoring
    -0.38
     Trotzdem
    -0.37
     definiti
    -0.37
    InstanceState
    -0.36
    POSITIVE LOGITS
     للاسماء
    0.52
    awtextra
    0.51
    CrossRef
    0.48
    ↹
    0.48
     mergeFrom
    0.48
     onBind
    0.47
    setVerticalGroup
    0.45
    ChrTalk
    0.45
    Rasp
    0.44
    ThemeOverlay
    0.44
    Act Density 0.005%

    No Known Activations