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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations and initialisms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.92
    ToAction
    -0.82
     nonatomic
    -0.81
     BoxDecoration
    -0.77
    BeginContext
    -0.73
     StatefulWidget
    -0.73
     disambiguazione
    -0.72
    #+#
    -0.71
     препратки
    -0.71
    httphttps
    -0.68
    POSITIVE LOGITS
     quatre
    0.49
     fa
    0.43
    freopen
    0.42
     four
    0.41
    Fa
    0.41
     المعيارى
    0.41
    4
    0.41
     cuarta
    0.40
    Вар
    0.40
    EM
    0.40
    Act Density 0.003%

    No Known Activations