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

    Neuronpedia

    INDEX
    Explanations

    find name to determine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    でも
    0.90
     محاضره
    0.81
     حتی
    0.78
     പിന്നീട്
    0.78
     там
    0.78
    だから
    0.77
    Already
    0.73
    できる
    0.73
    넣
    0.73
    좀
    0.72
    POSITIVE LOGITS
    ことを
    1.66
     것이
    1.65
     것을
    1.63
    것
    1.60
     것
    1.59
    ことが
    1.48
     것에
    1.33
     것은
    1.33
     thing
    1.32
     것으로
    1.29
    Act Density 0.019%

    No Known Activations