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

    Neuronpedia

    INDEX
    Explanations

    copyright and image removal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AppRoutingModule
    -0.06
    __))
    -0.06
    .trade
    -0.06
    _pe
    -0.06
     rozum
    -0.06
    سیون
    -0.06
     IDF
    -0.06
    arguments
    -0.06
     insects
    -0.06
    สด
    -0.06
    POSITIVE LOGITS
    …↵
    0.07
    (Calendar
    0.07
     ways
    0.06
     slap
    0.06
     rtl
    0.06
    /products
    0.06
    '),↵
    0.06
    向
    0.06
     inappropriate
    0.06
     navigating
    0.06
    Act Density 0.001%

    No Known Activations