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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    س
    1.03
    ان
    0.88
    ن
    0.85
    ्स
    0.73
    g
    0.73
    ন
    0.71
    вано
    0.71
    র
    0.67
    j
    0.66
    éch
    0.66
    POSITIVE LOGITS
     aussitôt
    1.00
    奐
    0.94
     McKinsey
    0.86
    zovaniyu
    0.82
     этот
    0.82
     jalur
    0.81
     sitzt
    0.79
     Это
    0.79
     saída
    0.79
     ไหร่
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.