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

    Neuronpedia

    INDEX
    Explanations

    in exchange for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Quand
    1.37
    {
    1.21
    L
    1.12
    N
    1.11
     auront
    1.06
    '{
    1.05
    quando
    1.05
     eben
    1.04
    XIII
    1.04
    apply
    1.03
    POSITIVE LOGITS
    ра
    1.45
    джа
    1.26
     निभाने
    1.23
    дзе
    1.20
     বিনিম
    1.20
    ut
    1.20
    cen
    1.19
    交換
    1.16
    d
    1.15
    ма
    1.13
    Act Density 0.013%

    No Known Activations