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

    Neuronpedia

    INDEX
    Explanations

    beliefs and assumptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    販売
    -0.06
     seleccion
    -0.06
     beers
    -0.06
     '/';↵
    -0.06
    яс
    -0.06
    िल
    -0.06
    Sarah
    -0.06
    ीटर
    -0.06
     Sister
    -0.06
    ﺪ
    -0.06
    POSITIVE LOGITS
    addAction
    0.06
    >--
    0.06
    .graphics
    0.06
    Assigned
    0.06
    %=
    0.06
    [A
    0.06
     Пов
    0.06
     Madrid
    0.06
    (task
    0.06
    putc
    0.06
    Act Density 0.013%

    No Known Activations