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

    Neuronpedia

    INDEX
    Explanations

    grid layout medium screen size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    1.88
    al
    1.63
    el
    1.57
    ic
    1.56
    il
    1.48
    er
    1.45
    ar
    1.43
    em
    1.42
    ra
    1.42
    as
    1.33
    POSITIVE LOGITS
     доходов
    1.07
     jobSearch
    1.04
    рованного
    1.01
    Бе
    1.00
    рованный
    1.00
    க்ஸாண்ட
    1.00
    ்கலை
    0.98
     одежды
    0.97
     праздник
    0.97
     operandSize
    0.95
    Act Density 0.002%

    No Known Activations