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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —for
    -0.08
    连线
    -0.07
     ``(
    -0.07
     Хо
    -0.07
    _Of
    -0.07
    FieldValue
    -0.07
    SetValue
    -0.06
    巨型
    -0.06
    _Version
    -0.06
    血脉
    -0.06
    POSITIVE LOGITS
    ?'
    0.07
     inst
    0.07
    уш
    0.07
     attracted
    0.07
    ticks
    0.06
    'app
    0.06
    ,l
    0.06
    홛
    0.06
     dam
    0.06
    ened
    0.06
    Act Density 0.029%

    No Known Activations