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

    Neuronpedia

    INDEX
    Explanations

    Fat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -0.71
    inty
    -0.70
    al
    -0.59
    ical
    -0.59
    ness
    -0.58
    sters
    -0.58
    ing
    -0.57
    ants
    -0.57
    liant
    -0.57
    ting
    -0.56
    POSITIVE LOGITS
    MigrationBuilder
    0.88
     Мексичка
    0.76
     JpaRepository
    0.67
     cages
    0.64
    #+#
    0.63
    WithIOException
    0.63
    AccessorTable
    0.62
     समीक्षाओं
    0.62
     utafitiHapana
    0.61
    깐
    0.60
    Act Density 0.138%

    No Known Activations