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
    enant
    -0.08
     ("<
    -0.06
    만원
    -0.06
    ，但是
    -0.06
     Thiên
    -0.06
    uguay
    -0.06
     albums
    -0.06
     tamanho
    -0.06
     Kul
    -0.06
     Morton
    -0.06
    POSITIVE LOGITS
    -sex
    0.07
    -bre
    0.07
    oons
    0.07
     tolerated
    0.06
    TZ
    0.06
     }));↵↵
    0.06
     NK
    0.06
     να
    0.06
     independently
    0.06
    FIELDS
    0.06
    Act Density 0.002%

    No Known Activations