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

    Neuronpedia

    INDEX
    Explanations

    say working or work

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    outh
    -0.08
    ICODE
    -0.06
     může
    -0.06
     peut
    -0.06
     ми
    -0.06
     معنی
    -0.06
     httpClient
    -0.06
     เก
    -0.06
    KeyEvent
    -0.06
     pleasures
    -0.06
    POSITIVE LOGITS
     laz
    0.07
    									↵
    0.07
     dood
    0.06
    desk
    0.06
    .getUsername
    0.06
     retains
    0.06
    awks
    0.06
    inions
    0.06
     Poker
    0.06
     Moff
    0.06
    Act Density 0.033%

    No Known Activations