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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    나
    0.84
    </strong>
    0.83
    р
    0.78
    いない
    0.77
    </h3>
    0.76
     juga
    0.75
     tepat
    0.73
    а
    0.72
    AIRMAN
    0.70
    아
    0.70
    POSITIVE LOGITS
     sausages
    0.90
    millimeters
    0.88
     Lukaku
    0.79
    thand
    0.79
    бить
    0.77
    nouns
    0.77
     individualism
    0.77
    sack
    0.76
     Bakufu
    0.75
    ھوں
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.