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

    Neuronpedia

    INDEX
    Explanations

    CI P- or PI ):

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.32
    اً
    1.20
    ्स
    1.19
    ünün
    1.16
    ों
    1.16
    сний
    1.14
    EQ
    1.13
    OVER
    1.12
    ség
    1.09
    AIR
    1.07
    POSITIVE LOGITS
    ל
    1.36
     siquiera
    1.23
     pensado
    1.18
    んですよ
    1.14
    んじゃない
    1.13
    ра
    1.12
     positivos
    1.11
    ال
    1.09
    quele
    1.08
    と考え
    1.07
    Act Density 0.000%

    No Known Activations