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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Digital
    0.73
     Apply
    0.72
     Bakın
    0.71
    س
    0.68
    š
    0.68
    بي
    0.67
    ئة
    0.67
     س
    0.66
     Reasoning
    0.65
     Mainland
    0.64
    POSITIVE LOGITS
    AUTH
    1.01
    FAR
    0.81
    вары
    0.81
     большинства
    0.81
    fourths
    0.80
    浊
    0.80
    ஜ்மஹால்
    0.77
     इसे
    0.77
    Facet
    0.77
    并没有
    0.76
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.