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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ﺴ
    0.93
    ﻜ
    0.89
    ﺘ
    0.86
     女性
    0.80
     여성
    0.80
    ﺒ
    0.80
    ья
    0.79
    ﺮ
    0.78
     ப
    0.76
     男
    0.75
    POSITIVE LOGITS
    ();
    0.88
     whereby
    0.84
    দির
    0.79
    ন
    0.77
    ud
    0.77
     enjoyment
    0.77
     implemented
    0.74
     could
    0.73
     of
    0.72
     incorporates
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.