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
     Bodies
    -0.07
     Provider
    -0.07
     specializes
    -0.06
     cost
    -0.06
     Equip
    -0.06
     경기
    -0.06
     yapılması
    -0.06
    _stat
    -0.06
     AccessToken
    -0.06
     karıştır
    -0.06
    POSITIVE LOGITS
     arise
    0.07
     cubic
    0.07
    -main
    0.06
    067
    0.06
     watt
    0.06
    ()):↵
    0.06
     trif
    0.06
    千
    0.06
     overwrite
    0.06
    equalsIgnoreCase
    0.06
    Act Density 0.023%

    No Known Activations