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

    Neuronpedia

    INDEX
    Explanations

    parse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    这就是
    -0.08
    ItemAt
    -0.08
    _TITLE
    -0.07
    蒙
    -0.07
     Todos
    -0.07
    wagon
    -0.07
     That
    -0.07
    .loadtxt
    -0.07
    ([...
    -0.07
    迢
    -0.07
    POSITIVE LOGITS
    经济学
    0.07
    瘴
    0.07
    推出的
    0.06
     creature
    0.06
    㟁
    0.06
     tasting
    0.06
    $insert
    0.06
     Marketable
    0.06
    uga
    0.06
     pragma
    0.06
    Act Density 0.016%

    No Known Activations