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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ټول
    0.63
     pulpit
    0.61
    лып
    0.60
     worsens
    0.58
    FONT
    0.58
    ClrBit
    0.58
     selalu
    0.57
     COD
    0.57
     جميع
    0.56
     اعلی
    0.56
    POSITIVE LOGITS
    গরের
    0.75
    🏰
    0.70
    রামর্শ
    0.64
    iselle
    0.62
     RSVP
    0.61
     ద్వ
    0.60
     iler
    0.59
     rêve
    0.59
     ister
    0.59
     sentado
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.