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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     links
    -0.07
    λής
    -0.07
    stand
    -0.07
     파
    -0.06
     cửa
    -0.06
     first
    -0.06
     тур
    -0.06
     printers
    -0.06
    추
    -0.06
     khô
    -0.06
    POSITIVE LOGITS
    BACK
    0.07
    oksen
    0.06
    rm
    0.06
    (deg
    0.06
     enables
    0.06
    (PyObject
    0.06
     закон
    0.06
    Slider
    0.06
    ��
    0.06
    erece
    0.06
    Act Density 0.000%

    No Known Activations