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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鸣
    -0.07
     conject
    -0.07
    PARSE
    -0.07
     n
    -0.07
    üğ
    -0.06
    BOOK
    -0.06
     incred
    -0.06
    بحر
    -0.06
    _thresh
    -0.06
    ereo
    -0.06
    POSITIVE LOGITS
     pracownik
    0.07
     предлагает
    0.07
    坛
    0.07
    afort
    0.07
    特点是
    0.07
    ację
    0.07
    门槛
    0.06
    -launch
    0.06
    owied
    0.06
     özellik
    0.06
    Act Density 0.012%

    No Known Activations