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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ﺍ
    0.85
     मानदंड
    0.80
    knię
    0.77
     badan
    0.75
     సంబంధించిన
    0.75
     uye
    0.75
    什么
    0.74
     merupakan
    0.74
     xwe
    0.73
     पूछते
    0.72
    POSITIVE LOGITS
    ｃ
    0.72
    쁨
    0.72
    랏
    0.71
    론
    0.70
    ccess
    0.69
    ل
    0.69
    лт
    0.68
    디어
    0.68
     EntityManager
    0.68
     colectivo
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.