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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    يمة
    0.65
    ទទួលបាន
    0.57
    يلة
    0.53
     countrymen
    0.52
     warm
    0.51
     rewarded
    0.50
     agree
    0.50
    अन्य
    0.50
     vuurp
    0.49
     شده‌است
    0.49
    POSITIVE LOGITS
    ä
    0.84
    of
    0.68
    á
    0.64
    på
    0.60
    тік
    0.60
    à
    0.59
    larni
    0.58
    ł
    0.56
     của
    0.55
    𝕖
    0.55
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.