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

    Neuronpedia

    INDEX
    Explanations

    titles and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.68
     الحره
    -0.67
     مشين
    -0.66
     Efq
    -0.66
     myſelf
    -0.64
    ụp
    -0.63
     ویکی‌پدیای
    -0.61
     itſelf
    -0.59
     themſelves
    -0.58
     Reſ
    -0.58
    POSITIVE LOGITS
     Soll
    0.58
     Meksiku
    0.57
    WebControls
    0.57
    TypedDataSet
    0.56
    HasBeenSet
    0.54
     Law
    0.54
    jspb
    0.54
     gepubliceerd
    0.52
    addCriterion
    0.52
    Nonnull
    0.50
    Act Density 0.006%

    No Known Activations