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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StringBuilder
    -0.08
    ер
    -0.08
     standardized
    -0.07
    罗斯
    -0.07
     결과
    -0.06
     Placeholder
    -0.06
     itinerary
    -0.06
    /**↵
    -0.06
    FileSystem
    -0.06
    алось
    -0.06
    POSITIVE LOGITS
    swire
    0.06
    اوي
    0.06
    locate
    0.06
     ponds
    0.06
     acquaint
    0.06
     επα
    0.06
     endIndex
    0.06
    amazon
    0.06
    edik
    0.06
    	ext
    0.06
    Act Density 0.006%

    No Known Activations