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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ের
    0.86
     quartier
    0.77
    емости
    0.73
    sport
    0.72
     территории
    0.72
     marít
    0.71
    യുടെ
    0.70
    AUTHORIZED
    0.70
     impegno
    0.69
    ς
    0.69
    POSITIVE LOGITS
     so
    0.75
    所以
    0.70
    为什么
    0.70
     chết
    0.70
    如此
    0.68
     ofthe
    0.68
     why
    0.67
     compared
    0.66
    而不是
    0.65
    所以我
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.