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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     contatt
    0.82
     Também
    0.79
     vesc
    0.79
     fabb
    0.77
     vấn
    0.75
     tránh
    0.75
     verrà
    0.75
     Puoi
    0.75
     tutto
    0.74
     qualità
    0.73
    POSITIVE LOGITS
    س
    0.80
    ირი
    0.74
    л
    0.73
    ມ
    0.71
    uat
    0.71
     названия
    0.70
     नूर
    0.69
    ილი
    0.68
    ศ์
    0.68
    нести
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.