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

    Neuronpedia

    INDEX
    Explanations

    stopwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -types
    -0.07
    Tom
    -0.07
     Tampa
    -0.07
    ゴ
    -0.06
    HTTPRequestOperation
    -0.06
    δι
    -0.06
     Nile
    -0.06
    mma
    -0.06
    共和
    -0.06
    arı
    -0.06
    POSITIVE LOGITS
    駅徒歩
    0.07
     مختلف
    0.07
     waterfront
    0.06
    Started
    0.06
    .Location
    0.06
     airst
    0.06
     edilmiş
    0.06
    	None
    0.06
    =?";↵
    0.06
     canvas
    0.06
    Act Density 0.347%

    No Known Activations