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

    Neuronpedia

    INDEX
    Explanations

    standard C includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taw
    0.39
    Slip
    0.38
     [][]
    0.37
    [][]
    0.36
     ゙
    0.36
    atore
    0.36
     Slip
    0.36
     pp
    0.35
    }}[
    0.35
    pp
    0.35
    POSITIVE LOGITS
     strcpy
    0.54
    strcpy
    0.54
     préstamo
    0.41
     memset
    0.40
     সেনাবাহিনীকে
    0.40
    ята
    0.39
     lembra
    0.39
     lawyers
    0.39
     вспом
    0.39
     হতাশ
    0.38
    Act Density 0.000%

    No Known Activations