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

    Neuronpedia

    INDEX
    Explanations

    sorting algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    σσ
    1.07
    lend
    1.06
     multimillion
    1.04
    minded
    1.03
     voit
    1.02
    r
    1.02
    uff
    1.00
     riguard
    1.00
    setzen
    0.99
     फीसद
    0.99
    POSITIVE LOGITS
    澳洲
    1.10
     bilin
    1.08
     pn
    1.07
    ᱥ
    1.03
    ched
    1.02
    ozygous
    1.00
    λι
    0.99
    gradle
    0.99
    Famous
    0.98
    كل
    0.97
    Act Density 0.002%

    No Known Activations