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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    6
    0.77
     application
    0.77
     orientation
    0.74
    2
    0.73
    ories
    0.72
    י
    0.70
    ད
    0.69
    ს
    0.69
    ין
    0.67
     উদ্দেশ
    0.66
    POSITIVE LOGITS
    uette
    0.88
    찬가지
    0.88
    讣
    0.86
    큥
    0.83
     maksimum
    0.80
    ઁ
    0.80
     pions
    0.79
     maximale
    0.79
    ়া
    0.79
    許可
    0.78
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.