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

    Neuronpedia

    INDEX
    Explanations

    famous names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Jack
    -0.07
     первой
    -0.06
    TOTYPE
    -0.06
    кид
    -0.06
    Ki
    -0.06
    بين
    -0.06
    datas
    -0.06
     πως
    -0.06
    laus
    -0.06
    كي
    -0.06
    POSITIVE LOGITS
     opposed
    0.07
    !!!!!!!!
    0.07
     gouver
    0.07
    火
    0.07
     Telescope
    0.07
    unordered
    0.07
    .characters
    0.06
     smashed
    0.06
     opatření
    0.06
     ITEMS
    0.06
    Act Density 0.056%

    No Known Activations