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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ("",
    0.73
    ]+"
    0.71
    _);
    0.63
    ological
    0.63
    ಿಗೆ
    0.63
     tinc
    0.63
    cling
    0.61
    ()));
    0.60
    Name
    0.60
     BE
    0.59
    POSITIVE LOGITS
     Người
    0.88
     बताऊंगा
    0.83
     Vorsch
    0.81
    freie
    0.81
     күзгү
    0.80
    それで
    0.79
     ночью
    0.78
    рал
    0.78
     言っ
    0.78
    বাব
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.