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

    Neuronpedia

    INDEX
    Explanations

    consistent or repeated values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ùng
    -0.06
     Κά
    -0.06
     prefers
    -0.06
     Career
    -0.06
    headline
    -0.06
    Раз
    -0.06
    heimer
    -0.06
    egers
    -0.06
    ottenham
    -0.05
     وضع
    -0.05
    POSITIVE LOGITS
    realm
    0.07
    SystemService
    0.07
    _Array
    0.07
    otent
    0.06
     증
    0.06
    methods
    0.06
    /right
    0.06
    _gs
    0.06
     miesz
    0.06
    issenschaft
    0.06
    Act Density 0.021%

    No Known Activations