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

    Neuronpedia

    INDEX
    Explanations

    technical language, abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ancellationToken
    -0.07
     Shoe
    -0.07
     lấy
    -0.07
     rasp
    -0.06
     flop
    -0.06
     sever
    -0.06
    418
    -0.06
    ούς
    -0.06
    Borders
    -0.06
    806
    -0.06
    POSITIVE LOGITS
    имость
    0.06
     ویژگی
    0.06
    ітет
    0.06
    Magnitude
    0.06
     ป
    0.06
    ippo
    0.06
    тоф
    0.06
    _Release
    0.06
    UBLE
    0.06
    _CONN
    0.06
    Act Density 0.006%

    No Known Activations