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
     Trailer
    -0.07
    Extras
    -0.07
     frail
    -0.06
     qu
    -0.06
     μό
    -0.06
    with
    -0.06
    =====
    -0.06
     BOOST
    -0.06
     kop
    -0.06
     vidět
    -0.06
    POSITIVE LOGITS
    _OUT
    0.07
    _Position
    0.07
     Huffington
    0.06
     کارخانه
    0.06
    AxisSize
    0.06
     Ontario
    0.06
     Σχ
    0.06
     Michelle
    0.06
     NBC
    0.06
    чина
    0.06
    Act Density 0.068%

    No Known Activations