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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    מר
    0.52
    мере
    0.50
    веден
    0.50
    ু
    0.50
    не
    0.50
    לו
    0.50
    גל
    0.50
    ק
    0.49
    би
    0.48
    ुद्ध
    0.48
    POSITIVE LOGITS
    ↵
    0.60
    Ak
    0.55
    ac
    0.48
     Produkt
    0.48
    Hold
    0.47
    Jpa
    0.46
     Foto
    0.46
    ‟
    0.46
    Hin
    0.45
     Partei
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.