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

    Neuronpedia

    INDEX
    Explanations

    1 or 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .changed
    -0.07
     salir
    -0.07
     penned
    -0.07
     procedures
    -0.06
    )↵↵↵↵
    -0.06
     transportation
    -0.06
     lower
    -0.06
    ));↵↵↵
    -0.06
     박
    -0.06
    emes
    -0.06
    POSITIVE LOGITS
    Locale
    0.07
    edm
    0.06
    duct
    0.06
    =models
    0.06
    _lr
    0.06
    pill
    0.06
    งเป
    0.06
     Joi
    0.06
    енко
    0.06
    يدا
    0.06
    Act Density 0.008%

    No Known Activations