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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    a
    0.92
    ی
    0.92
    ков
    0.89
    igns
    0.82
    inned
    0.80
    тер
    0.79
    рый
    0.79
    ح
    0.78
    ה
    0.77
    го
    0.76
    POSITIVE LOGITS
     Những
    0.93
     Toutes
    0.90
     incroyable
    0.87
    拃
    0.86
     professeur
    0.83
    nX
    0.83
    ただ
    0.83
     décisions
    0.82
     Marietta
    0.81
     attraverso
    0.81
    Act Density 0.000%

    No Known Activations