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

    Neuronpedia

    INDEX
    Explanations

    latex math notation

    oai_token-act-pair · gemini-2.0-flash

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __':
    -0.93
    .*")]
    -0.83
    __':
    -0.82
    parsedMessage
    -0.81
     مشارکت‌کنندگان
    -0.81
    __":
    -0.80
    RunWith
    -0.77
    __":
    -0.76
    ValueStyle
    -0.76
     ویکی‌پدیای
    -0.75
    POSITIVE LOGITS
    C
    0.40
    넷
    0.40
    S
    0.38
    Inflater
    0.36
    a
    0.35
    [
    0.35
    T
    0.35
    V
    0.35
    A
    0.35
    E
    0.35
    Act Density 2.398%

    No Known Activations