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

    Neuronpedia

    INDEX
    Explanations

    module require

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     empire
    -0.07
     paddingBottom
    -0.07
     продуктов
    -0.07
    ć
    -0.06
    อกจาก
    -0.06
    ::_
    -0.06
    _shutdown
    -0.06
    /,
    -0.06
    izr
    -0.06
    عه
    -0.06
    POSITIVE LOGITS
    aker
    0.07
    HR
    0.06
    OND
    0.06
    オリ
    0.06
    сих
    0.06
    0.06
     τη
    0.06
    OLER
    0.06
    ering
    0.06
    psych
    0.06
    Act Density 0.142%

    No Known Activations