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

    Neuronpedia

    INDEX
    Explanations

    Wild West

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dictate
    0.55
     anglais
    0.55
     endoplasmic
    0.55
     convirtió
    0.54
    పతి
    0.54
     atheist
    0.52
     extrapolate
    0.51
    führt
    0.51
    "
    0.51
    ロップ
    0.50
    POSITIVE LOGITS
     Μ
    0.73
     Muay
    0.73
    و
    0.69
    多く
    0.68
     Association
    0.68
    ース
    0.67
     Basketball
    0.67
     Newsletter
    0.66
     BMX
    0.65
     of
    0.64
    Act Density 0.000%

    No Known Activations