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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AS
    -0.08
    전
    -0.07
    iap
    -0.07
     playoff
    -0.07
    -worthy
    -0.07
    'T
    -0.06
     Laden
    -0.06
    seys
    -0.06
    etic
    -0.06
    wegian
    -0.06
    POSITIVE LOGITS
    .SO
    0.07
     MainMenu
    0.07
     ------------------------------------------------------------
    0.06
     urlencode
    0.06
     POSIX
    0.06
    +</
    0.06
     ----------------------------------------------------------------------↵
    0.06
     vybav
    0.06
    (Menu
    0.06
    intval
    0.06
    Act Density 0.000%

    No Known Activations