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

    Neuronpedia

    INDEX
    Explanations

    Eight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অধিদ
    0.44
    uksi
    0.42
    㬶
    0.39
    IOR
    0.38
    ujących
    0.38
    ﱢ
    0.37
     चौपट
    0.37
    вших
    0.37
    再说
    0.37
     passieren
    0.36
    POSITIVE LOGITS
     Eight
    0.43
     बात
    0.43
    ८
    0.42
    八
    0.41
    8
    0.40
     八
    0.39
     Seven
    0.38
     ۸
    0.37
    ৮
    0.37
    ８
    0.37
    Act Density 0.164%

    No Known Activations