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
    建築
    -0.08
     Rugby
    -0.07
    .Go
    -0.06
     apps
    -0.06
    rega
    -0.06
    Es
    -0.06
    osals
    -0.06
    alc
    -0.06
     beyond
    -0.06
     invokingState
    -0.06
    POSITIVE LOGITS
    深圳
    0.07
     Tỉnh
    0.06
    (manager
    0.06
    _UID
    0.06
     subtly
    0.06
    *',
    0.06
     Doğum
    0.06
     тер
    0.06
    ////////////////////////////////////////////////////////////////////////////////↵↵
    0.06
    	parameters
    0.06
    Act Density 0.010%

    No Known Activations