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

    Neuronpedia

    INDEX
    Explanations

    Republican

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _markers
    -0.07
     kaufen
    -0.07
     Kiş
    -0.06
     Gray
    -0.06
     GmbH
    -0.06
    เล
    -0.06
     =========================================================================
    -0.06
     floating
    -0.06
    -0.06
     Basket
    -0.06
    POSITIVE LOGITS
     Лю
    0.06
    _reporting
    0.06
    (PyObject
    0.06
     ру
    0.06
     موسی
    0.06
    (iParam
    0.06
    財
    0.06
    tiv
    0.06
    TE
    0.06
    lh
    0.06
    Act Density 0.001%

    No Known Activations