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

    Neuronpedia

    INDEX
    Explanations

    transforms into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अवतार
    0.38
     পরেই
    0.38
     इससे
    0.37
     Aung
    0.36
     loud
    0.35
    是从
    0.35
    ია
    0.34
    loud
    0.33
    ুক্ত
    0.33
     differed
    0.33
    POSITIVE LOGITS
     into
    2.09
    into
    1.76
    Into
    1.72
     Into
    1.59
     इनटू
    1.45
     vào
    1.35
     INTO
    1.35
    转化为
    0.89
     превра
    0.86
     Vào
    0.83
    Act Density 0.035%

    No Known Activations