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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dingen
    0.67
     disebut
    0.66
     зри
    0.63
    ೋಪ
    0.62
     finanzi
    0.62
    ជ
    0.61
     voy
    0.60
     allt
    0.59
    væ
    0.59
     élevées
    0.58
    POSITIVE LOGITS
     Concrete
    0.73
    owanej
    0.73
     確認
    0.71
     情報
    0.70
    (`
    0.69
    abhavam
    0.69
     पूछता
    0.66
     Такой
    0.66
    翀
    0.66
     Meaning
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.