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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    א
    0.89
    و
    0.81
     perfekte
    0.80
    ف
    0.80
    ␶
    0.80
    лих
    0.79
    ش
    0.79
    ドレス
    0.79
    وارد
    0.78
    िमम
    0.75
    POSITIVE LOGITS
     Piaget
    0.88
     পোষণ
    0.84
     Salsa
    0.80
     Opus
    0.78
     Heels
    0.74
    沼
    0.73
     Amaz
    0.73
     paheli
    0.73
     Soho
    0.73
     Bora
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.