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

    Neuronpedia

    INDEX
    Explanations

    women

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sprite
    -0.07
     polish
    -0.07
     millenn
    -0.06
     sour
    -0.06
     producto
    -0.06
    pure
    -0.06
     얼
    -0.06
    rani
    -0.06
     brutal
    -0.06
    .HashMap
    -0.06
    POSITIVE LOGITS
     등록
    0.07
     effective
    0.07
     pData
    0.06
     �
    0.06
    분석
    0.06
    Among
    0.06
     Sizes
    0.06
    Traditional
    0.06
    ."↵↵↵↵
    0.06
    слов
    0.06
    Act Density 0.104%

    No Known Activations