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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     नई
    0.75
    iderman
    0.66
     liberated
    0.64
    नई
    0.63
     অপরদিকে
    0.61
    老
    0.60
     नयी
    0.60
     আগ্র
    0.60
     війни
    0.60
    的女
    0.59
    POSITIVE LOGITS
     เช่น
    0.74
     sechs
    0.71
    :
    0.68
     Objekte
    0.66
     podstaw
    0.66
     บาง
    0.65
     ถ้า
    0.63
     dần
    0.63
     フォト
    0.63
     sikk
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.