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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _launcher
    -0.07
    elseif
    -0.07
    DataContext
    -0.07
     Dipl
    -0.07
     yup
    -0.06
     upt
    -0.06
     всю
    -0.06
    heartbeat
    -0.06
     handicap
    -0.06
    _BUTTON
    -0.06
    POSITIVE LOGITS
    (edit
    0.07
    5
    0.07
     menus
    0.07
    .green
    0.06
    리는
    0.06
    aining
    0.06
    enci
    0.06
     cork
    0.06
    :user
    0.06
     المج
    0.06
    Act Density 0.001%

    No Known Activations