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

    Neuronpedia

    INDEX
    Explanations

    tele

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أثن
    -0.07
     viewPager
    -0.07
    ՞
    -0.07
    满怀
    -0.07
    帙
    -0.07
     ран
    -0.07
     carbohydr
    -0.07
    新城
    -0.06
    +","+
    -0.06
     illum
    -0.06
    POSITIVE LOGITS
    ℏ
    0.09
     legality
    0.08
    كات
    0.08
    	position
    0.07
    ли
    0.07
    トリ
    0.07
    ey
    0.07
    taken
    0.07
    ⋯
    0.07
    Honestly
    0.07
    Act Density 0.006%

    No Known Activations