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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bituminous
    0.49
     inventories
    0.48
     bolstering
    0.47
     افضل
    0.47
     ممتاز
    0.46
     bids
    0.46
     “‘
    0.45
     ಸುಬ್ಬ
    0.45
     بهتر
    0.44
     ಕಂಚ
    0.44
    POSITIVE LOGITS
    เพ
    0.45
    са
    0.44
    p
    0.43
    ถ้า
    0.42
     élect
    0.42
    フ
    0.42
    Triple
    0.41
    ขา
    0.41
     образом
    0.41
    aled
    0.40
    Act Density 0.010%

    No Known Activations