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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    方方面面
    -0.07
    鳚
    -0.07
     werden
    -0.07
    hopefully
    -0.07
    aign
    -0.06
    DisplayName
    -0.06
    ייט
    -0.06
    恩
    -0.06
    AND
    -0.06
    AttributeName
    -0.06
    POSITIVE LOGITS
    _icons
    0.07
    厣
    0.07
    -Based
    0.07
     risking
    0.07
    仍然是
    0.07
     Modal
    0.07
     salute
    0.06
    (other
    0.06
    :**
    0.06
    .Re
    0.06
    Act Density 0.026%

    No Known Activations