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

    Neuronpedia

    INDEX
    Explanations

    technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gender
    -0.07
     sty
    -0.07
     frequency
    -0.06
     accusations
    -0.06
    ashes
    -0.06
     expresses
    -0.06
     andre
    -0.06
     clockwise
    -0.06
     held
    -0.06
    Params
    -0.06
    POSITIVE LOGITS
    LEE
    0.07
    _SHARE
    0.07
    хов
    0.07
    /releases
    0.07
     dinosaur
    0.06
     Ну
    0.06
     Sears
    0.06
    771
    0.06
    LOWER
    0.06
    /e
    0.06
    Act Density 0.000%

    No Known Activations