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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ǧ
    -0.07
     journals
    -0.07
    jenis
    -0.07
    ʾ
    -0.07
    /assets
    -0.07
     confess
    -0.07
     tah
    -0.07
     migrated
    -0.07
     Margaret
    -0.07
    纵
    -0.07
    POSITIVE LOGITS
    ϗ
    0.07
    밟
    0.07
    _]
    0.07
    睁开
    0.07
    экон
    0.07
     starts
    0.07
     {↵↵↵
    0.06
     działal
    0.06
    _attack
    0.06
    まだまだ
    0.06
    Act Density 0.001%

    No Known Activations