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

    Neuronpedia

    INDEX
    Explanations

    pandas DataFrame and Series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ),
    0.84
    AC
    0.82
    1
    0.73
    ?),
    0.70
     August
    0.68
     q
    0.67
    ),"
    0.67
     IQR
    0.67
    ）,
    0.66
     Include
    0.64
    POSITIVE LOGITS
    ная
    0.90
    िया
    0.77
    ೀ
    0.77
    できる
    0.75
    اری
    0.75
    (
    0.73
    社の
    0.72
    ération
    0.71
     viennent
    0.70
    ным
    0.70
    Act Density 0.019%

    No Known Activations