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

    Neuronpedia

    INDEX
    Explanations

    variable names in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ferrugineux
    0.30
    𒄀
    0.29
    ategorie
    0.29
     น้ํา
    0.29
     เรื่อง
    0.27
     ܒ
    0.27
    ouncil
    0.27
     Elektrokhimiya
    0.27
    Mât
    0.26
    摀
    0.26
    POSITIVE LOGITS
     clog
    0.30
     whose
    0.29
     tails
    0.29
     usually
    0.28
     substrings
    0.28
     first
    0.27
     again
    0.27
     shuffle
    0.27
     numbers
    0.26
     chunks
    0.26
    Act Density 0.227%

    No Known Activations