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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     entrar
    0.79
    n
    0.75
     vai
    0.74
    ljena
    0.72
    ilah
    0.72
    ohan
    0.71
     derece
    0.71
    airi
    0.70
     Rath
    0.70
    ில்
    0.69
    POSITIVE LOGITS
    ስ
    0.75
    マリン
    0.74
    Основ
    0.73
     भर्त
    0.73
    лта
    0.72
    ECTION
    0.72
     създа
    0.71
     TInner
    0.71
     liberties
    0.70
    ству
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.