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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     edit
    -0.06
     Trong
    -0.06
     negative
    -0.06
    安
    -0.06
     current
    -0.06
     informações
    -0.06
     martin
    -0.06
    保证
    -0.06
    _year
    -0.06
    _GRAPH
    -0.06
    POSITIVE LOGITS
    Ÿ
    0.07
    ailing
    0.07
    Ÿ
    0.07
     Steelers
    0.06
     koşul
    0.06
    //[
    0.06
     gained
    0.06
    ा
    0.06
    _soup
    0.06
    QT
    0.06
    Act Density 0.002%

    No Known Activations