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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     साथ
    1.57
     боль
    1.52
    relatively
    1.49
    ޏ
    1.48
     proverb
    1.42
     occupiers
    1.39
    sacrifice
    1.39
    چی
    1.35
    ২৫
    1.35
    Боль
    1.29
    POSITIVE LOGITS
    𝐭
    1.72
    betrieb
    1.58
    dling
    1.54
    alnya
    1.53
     ενός
    1.53
     ✔
    1.50
     sprzedaży
    1.49
    ص
    1.49
    𝐚
    1.49
     anmelden
    1.48
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.