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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    可能
    -0.07
    .maximum
    -0.06
     fluctuations
    -0.06
     Invalidate
    -0.06
     đường
    -0.06
    .drawRect
    -0.06
     гип
    -0.06
    kenin
    -0.06
     سیاسی
    -0.06
     Và
    -0.06
    POSITIVE LOGITS
     {});↵↵
    0.07
     eux
    0.06
     eskort
    0.06
     Aster
    0.06
    Dam
    0.06
     всем
    0.06
    (headers
    0.06
    zed
    0.06
    šek
    0.06
    ับม
    0.06
    Act Density 0.014%

    No Known Activations