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

    Neuronpedia

    INDEX
    Explanations

    avatar expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.45
    ी
    1.29
     Scattering
    1.20
     reckoned
    1.19
     সারা
    1.18
     Ра
    1.13
     С
    1.11
    י
    1.10
     Körper
    1.09
     trafficking
    1.09
    POSITIVE LOGITS
    αν
    1.14
     celebrity
    1.12
    ply
    1.11
    emphas
    1.10
    mouseDown
    1.10
    ρας
    1.10
    ۰۰
    1.10
     μιας
    1.09
     σχετικά
    1.09
     separa
    1.08
    Act Density 0.000%

    No Known Activations