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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     taxon
    0.72
     خار
    0.71
    我们将
    0.70
    الم
    0.70
    που
    0.69
    DONE
    0.69
    你想
    0.68
    अ
    0.67
    ごと
    0.67
     solle
    0.67
    POSITIVE LOGITS
    bmatrix
    0.63
     demikian
    0.60
    ਼
    0.59
    цию
    0.58
    тинг
    0.58
     ibid
    0.58
    ூன்
    0.57
    циях
    0.57
    ční
    0.57
    ज्ञ
    0.56
    Act Density 0.003%

    No Known Activations