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

    Neuronpedia

    INDEX
    Explanations

    colons, equations, and other mathematical or list-based symbols.

    oai_token-act-pair · gemini-2.0-flash

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ‘
    -0.41
    DoubleQuotes
    -0.39
     cópia
    -0.39
    олові
    -0.39
    vič
    -0.38
     .=
    -0.36
    kJ
    -0.36
    『
    -0.36
    kapet
    -0.36
     Т
    -0.36
    POSITIVE LOGITS
    FunctionFlags
    0.79
     myſelf
    0.76
     Jefus
    0.75
    ContentAsync
    0.75
    CppMethod
    0.75
     faſt
    0.75
     purpoſe
    0.74
     дописавши
    0.74
     Eſ
    0.73
     ſtand
    0.73
    Act Density 4.482%

    No Known Activations