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

    Neuronpedia

    INDEX
    Explanations

    code/data files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    astle
    -0.06
     اختص
    -0.06
    operand
    -0.06
    럽
    -0.06
     matchup
    -0.06
     enthusiast
    -0.06
     jealous
    -0.06
     uc
    -0.06
     musicians
    -0.06
    ognition
    -0.06
    POSITIVE LOGITS
    ，将
    0.07
     qed
    0.07
    Tại
    0.06
    	className
    0.06
    ']>
    0.06
    \data
    0.06
    слов
    0.06
     nous
    0.06
     làn
    0.06
    	Point
    0.06
    Act Density 0.032%

    No Known Activations