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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ܘ
    1.00
    ョ
    0.99
     Indian
    0.97
     동
    0.95
     ニュー
    0.95
    ්
    0.95
    ズ
    0.94
    flip
    0.94
     New
    0.93
    ྨ
    0.92
    POSITIVE LOGITS
     sufr
    1.15
    Fechar
    1.12
    kość
    1.10
     swells
    1.09
     actuación
    1.07
    otricha
    1.04
     ácido
    1.04
    芜
    1.03
     uscita
    1.02
     adopté
    1.02
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.