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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     walls
    -0.47
    ništ
    -0.45
    nestjs
    -0.44
    psack
    -0.44
     headers
    -0.44
     points
    -0.44
     tombol
    -0.43
    点了
    -0.43
     hindsight
    -0.43
     jump
    -0.43
    POSITIVE LOGITS
    OGND
    0.74
    awtextra
    0.71
    +#+#
    0.71
    DockStyle
    0.70
    MigrationBuilder
    0.65
     المعيارى
    0.64
    LookAnd
    0.60
     Lokales
    0.59
    KommentareTeilen
    0.59
     typelib
    0.59
    Act Density 0.031%

    No Known Activations