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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    y
    0.39
    is
    0.38
     He
    0.36
     Clothing
    0.36
    w
    0.36
    si
    0.35
    pere
    0.35
     Veil
    0.35
    sub
    0.35
     fruto
    0.35
    POSITIVE LOGITS
    বিষ্য
    0.35
    跶
    0.35
     matching
    0.34
    ilizce
    0.34
    বৈশাখ
    0.34
     proliferating
    0.34
    োধী
    0.34
    chedules
    0.34
     noqa
    0.34
     awarding
    0.33
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.