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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    toothpaste
    1.59
     ssid
    1.59
    丷
    1.46
    𝙨
    1.44
    ಬ್ಬಿಣ
    1.42
     местности
    1.41
    kook
    1.40
    धाम
    1.40
     Tahoe
    1.39
     bitOp
    1.39
    POSITIVE LOGITS
     measured
    1.00
    க்கு
    0.97
    ிட
    0.97
    方
    0.93
    ادرة
    0.89
    з
    0.87
     headache
    0.86
    方の
    0.86
     घटकर
    0.85
     भरा
    0.85
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.