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

    Neuronpedia

    INDEX
    Explanations

    work patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ized
    1.28
    الإ
    1.28
    る
    1.20
    ی
    1.11
    การ
    1.08
    1.07
    ce
    1.06
    IC
    1.06
    І
    1.05
    coordinate
    1.05
    POSITIVE LOGITS
    ੀ
    1.37
    oqu
    1.34
    ings
    1.29
    𝙮
    1.27
    adid
    1.25
     logrado
    1.22
    y
    1.21
     adanya
    1.20
     otten
    1.17
    𝚕
    1.16
    Act Density 0.019%

    No Known Activations