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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    。
    0.82
    د
    0.80
    م
    0.68
    ش
    0.67
    ো
    0.66
    ။
    0.66
    ف
    0.65
    o
    0.64
    ،
    0.64
    প
    0.63
    POSITIVE LOGITS
     vždy
    1.05
     velocità
    0.98
     sempre
    0.91
     всегда
    0.89
     largura
    0.86
     любую
    0.84
     alltid
    0.83
    fdPar
    0.81
     selalu
    0.81
     либо
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.