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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     redesigned
    0.39
    стан
    0.38
    Smoke
    0.38
     Janet
    0.38
     lunch
    0.36
    Lunch
    0.36
    ሺ
    0.35
    వె
    0.35
    Personnel
    0.34
    Voices
    0.34
    POSITIVE LOGITS
     uska
    0.65
    不利
    0.40
     जियोग्राफी
    0.39
     Aprove
    0.38
     কালিক
    0.38
     насла
    0.37
     بينهم
    0.37
    सनीय
    0.37
     कुटु
    0.36
    ادو
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.