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

    Neuronpedia

    INDEX
    Explanations

    Scraped text/advertisements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imagen
    -0.07
    /apache
    -0.07
    	option
    -0.07
    Categoria
    -0.07
     мол
    -0.07
    общ
    -0.07
     satellite
    -0.06
    _sf
    -0.06
     seguir
    -0.06
    زيز
    -0.06
    POSITIVE LOGITS
     fools
    0.06
     Truly
    0.06
    ebo
    0.06
     Riy
    0.06
     worm
    0.06
     피해
    0.06
    ุ์
    0.06
    Damn
    0.06
    erville
    0.06
    avour
    0.06
    Act Density 0.038%

    No Known Activations