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

    Neuronpedia

    INDEX
    Explanations

    attributable Fat Shape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    1.11
     enthal
    1.11
     adhes
    1.08
     pana
    1.07
    ין
    1.06
     effectuées
    1.05
     QuantityOnHand
    1.04
    ر
    1.04
    Ammo
    1.03
    לח
    1.03
    POSITIVE LOGITS
     불구하고
    1.13
     Давайте
    1.08
     চেয়ারম্যান
    1.05
    \[
    1.05
     نموذ
    0.99
     آدمی
    0.99
    大会
    0.98
     بالغ
    0.98
     দা
    0.97
     즉
    0.97
    Act Density 0.000%

    No Known Activations