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

    Neuronpedia

    INDEX
    Explanations

    sex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kurtar
    -0.08
     analý
    -0.07
     Kendrick
    -0.07
     게시판
    -0.07
     zaměstnan
    -0.07
     opatření
    -0.07
     Biden
    -0.07
    plain
    -0.07
    -book
    -0.07
     поперед
    -0.07
    POSITIVE LOGITS
     sex
    0.18
     Sex
    0.18
    Sex
    0.15
     SEX
    0.12
    sex
    0.10
     sexes
    0.10
    -sex
    0.10
    _sex
    0.10
    alsex
    0.09
    sx
    0.09
    Act Density 0.025%

    No Known Activations