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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝘵
    2.81
    erà
    2.69
    ীয়
    2.67
    ヤー
    2.66
    ार्किक
    2.64
    ہور
    2.51
    na
    2.47
    ární
    2.47
    കോ
    2.44
    ty
    2.42
    POSITIVE LOGITS
    i
    3.40
    ו
    3.39
    সংখ্য
    3.17
    ಿ
    2.69
    es
    2.63
    ுகளை
    2.62
    ー
    2.53
    luents
    2.52
    a
    2.51
    ス
    2.50
    Act Density 0.709%

    No Known Activations