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

    Neuronpedia

    INDEX
    Explanations

    enterprise applications and teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ない
    3.09
    ありません
    2.47
    ないので
    2.36
    nél
    2.27
    nol
    2.22
    nál
    2.19
    ないと
    2.17
    nij
    2.13
     itulah
    2.11
    情况下
    2.06
    POSITIVE LOGITS
    pped
    2.34
     Außerdem
    2.33
    an
    2.28
    ю
    2.22
    ли
    2.19
    يد
    2.14
    ല്ലാം
    2.13
    ać
    2.08
    ל
    1.98
    л
    1.91
    Act Density 0.221%

    No Known Activations