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

    Neuronpedia

    INDEX
    Explanations

    server error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     República
    0.79
     OFW
    0.79
     Announced
    0.78
    yyam
    0.71
    闥
    0.70
     المن
    0.68
    presentableId
    0.68
     Dorey
    0.66
    Republic
    0.66
    спублі
    0.65
    POSITIVE LOGITS
     error
    1.08
     エ
    1.02
     erro
    0.92
    LaTeX
    0.86
    error
    0.86
    エラー
    0.82
    错误
    0.80
     errors
    0.79
     er
    0.78
     lỗi
    0.78
    Act Density 0.001%

    No Known Activations