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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     such
    0.73
     other
    0.71
     oder
    0.69
    たと
    0.63
     otras
    0.62
    場合に
    0.61
    場合は
    0.61
     misalnya
    0.59
     or
    0.58
    /
    0.58
    POSITIVE LOGITS
    Arts
    0.78
    Fetch
    0.74
     науки
    0.74
    文學
    0.73
    Attr
    0.73
     interdiscipl
    0.73
    Social
    0.73
    科学
    0.71
    Avg
    0.71
    Medicine
    0.71
    Act Density 0.000%

    No Known Activations