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

    Neuronpedia

    INDEX
    Explanations

    mod-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ang
    1.55
    ab
    1.23
    ка
    1.14
    ak
    1.13
     Без
    1.10
    ade
    1.07
     Τ
    1.06
     Что
    1.05
     Ρ
    1.04
     Бере
    1.03
    POSITIVE LOGITS
    ל
    1.64
    ни
    1.63
    К
    1.56
    ک
    1.50
    க
    1.20
     up
    1.19
    О
    1.19
    "
    1.15
    ১৯
    1.09
     be
    1.07
    Act Density 0.000%

    No Known Activations