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

    Neuronpedia

    INDEX
    Explanations

    SAT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;font
    -0.07
     soo
    -0.07
    铱
    -0.07
    出版
    -0.06
    第五
    -0.06
    𝓫
    -0.06
    俊
    -0.06
    Tex
    -0.06
    Occ
    -0.06
    atica
    -0.06
    POSITIVE LOGITS
    俄乌
    0.08
     lớp
    0.07
     salir
    0.07
    WebHost
    0.07
     handler
    0.07
    .Camera
    0.07
     nhật
    0.07
    壹
    0.07
    مير
    0.07
    	Object
    0.07
    Act Density 0.003%

    No Known Activations