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

    Neuronpedia

    INDEX
    Explanations

    code fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    зо
    -0.10
    另一方面
    -0.09
    through
    -0.08
    akwa
    -0.08
    看看
    -0.08
    CHANTABILITY
    -0.08
    зи
    -0.08
    	height
    -0.08
    ，看
    -0.08
    密码
    -0.08
    POSITIVE LOGITS
     contiguous
    0.08
     Nong
    0.08
     aggregated
    0.08
     aggregate
    0.07
     buffering
    0.07
     aggregates
    0.07
     Aggreg
    0.07
     movie
    0.07
     comprising
    0.07
     Temporary
    0.07
    Act Density 0.002%

    No Known Activations