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

    Neuronpedia

    INDEX
    Explanations

    knox, knock, knot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    blauch
    -0.84
     exhibition
    -0.80
    autoComplete
    -0.79
    وة
    -0.77
    Studies
    -0.77
     Varsity
    -0.73
    вот
    -0.73
     Healing
    -0.71
    قیمت
    -0.71
     Expressions
    -0.71
    POSITIVE LOGITS
    Kno
    1.09
     Kno
    1.02
     kno
    0.93
    kno
    0.88
     Knox
    0.85
    knock
    0.85
    Knock
    0.80
    Knox
    0.78
     knock
    0.77
     Knock
    0.76
    Act Density 0.018%

    No Known Activations