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

    Neuronpedia

    INDEX
    Explanations

    foreign language scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ممتاز
    0.53
     ಸುಬ್ಬ
    0.50
     ಕಂಚ
    0.50
     inventories
    0.48
     bids
    0.48
     bituminous
    0.46
    0.46
    ა
    0.46
    ulkner
    0.45
     افضل
    0.44
    POSITIVE LOGITS
    ถ้า
    0.49
    p
    0.47
     ahorita
    0.47
    注意
    0.46
     giả
    0.46
    フ
    0.45
     élect
    0.45
    os
    0.44
    сси
    0.44
     образом
    0.44
    Act Density 0.000%

    No Known Activations