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

    Neuronpedia

    INDEX
    Explanations

    math formulas and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    бурге
    0.29
    atedral
    0.28
    ätta
    0.27
    াহিয়া
    0.27
    segaretro
    0.27
    ുകളില്‍
    0.27
     marketplaces
    0.26
    ধানা
    0.26
    antoor
    0.25
    malıdır
    0.25
    POSITIVE LOGITS
     +
    0.35
    +
    0.34
     and
    0.31
     &
    0.30
     AND
    0.30
    +\
    0.28
     и
    0.27
     $+$
    0.26
    \
    0.26
     \
    0.26
    Act Density 0.257%

    No Known Activations