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
     Franc
    -0.08
     machines
    -0.07
    ipmap
    -0.07
    _lvl
    -0.07
    تبال
    -0.07
    ुर
    -0.07
    platform
    -0.07
     emergency
    -0.06
     Household
    -0.06
    \Test
    -0.06
    POSITIVE LOGITS
     Elm
    0.07
     由
    0.06
    体系
    0.06
    ємо
    0.06
     damned
    0.06
    .".
    0.06
     пользователя
    0.06
     sudoku
    0.06
     Milli
    0.06
     centrally
    0.06
    Act Density 0.000%

    No Known Activations