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

    Neuronpedia

    INDEX
    Explanations

    os

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,W
    -0.07
     như
    -0.07
     hl
    -0.07
    _ratio
    -0.06
    ！↵↵
    -0.06
    !',
    -0.06
    (Test
    -0.06
    ത
    -0.06
    ユーザ
    -0.06
    _candidates
    -0.06
    POSITIVE LOGITS
     única
    0.07
    parameters
    0.07
     Royals
    0.07
     الشركات
    0.07
     Lenin
    0.07
     saç
    0.07
     Ink
    0.07
     والا
    0.07
    _serial
    0.07
    必不可
    0.07
    Act Density 0.001%

    No Known Activations