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

    Neuronpedia

    INDEX
    Explanations

    statistics, math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    όν
    -0.08
     Appliances
    -0.07
    選
    -0.06
    reement
    -0.06
    赤
    -0.06
     geç
    -0.06
     jurisdiction
    -0.06
     planners
    -0.06
     TZ
    -0.06
    推荐
    -0.06
    POSITIVE LOGITS
    [data
    0.06
    dyby
    0.06
    lay
    0.06
     /*!<
    0.06
     Netanyahu
    0.06
     Montana
    0.06
    	Query
    0.06
    -------------
    0.06
     paperwork
    0.05
     Unlock
    0.05
    Act Density 0.014%

    No Known Activations