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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    های
    -0.07
     Lawyer
    -0.07
     모
    -0.07
    MainMenu
    -0.06
    .PrintWriter
    -0.06
     Costco
    -0.06
     Львів
    -0.06
     BJ
    -0.06
    онов
    -0.06
    _player
    -0.06
    POSITIVE LOGITS
     unused
    0.07
    έργ
    0.07
     Powell
    0.07
    经营
    0.07
    .flex
    0.06
     garment
    0.06
    .StringVar
    0.06
    Vict
    0.06
     безопас
    0.06
    UNCTION
    0.06
    Act Density 0.018%

    No Known Activations