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

    Neuronpedia

    INDEX
    Explanations

    descriptions and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stick
    -0.07
    Prince
    -0.07
     Tower
    -0.07
     sticks
    -0.06
     dumb
    -0.06
    上帝
    -0.06
    两项
    -0.06
     mower
    -0.06
     Upon
    -0.06
    עצב
    -0.06
    POSITIVE LOGITS
    _todo
    0.07
    {lng
    0.07
    	RTLR
    0.07
     우리나라
    0.07
    gı
    0.07
    .setStyleSheet
    0.07
    .writ
    0.07
    (PDO
    0.07
    هائي
    0.07
    在国内
    0.07
    Act Density 0.106%

    No Known Activations