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

    Neuronpedia

    INDEX
    Explanations

    City/University names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repr
    -0.07
     Почем
    -0.07
    岜
    -0.07
    .choice
    -0.07
    ということ
    -0.07
    どんど
    -0.06
     nghè
    -0.06
    .external
    -0.06
    䏲
    -0.06
    公开招聘
    -0.06
    POSITIVE LOGITS
    -written
    0.08
     comunidad
    0.07
    LAT
    0.07
     NONE
    0.07
     (↵↵
    0.07
     Needs
    0.07
     bunker
    0.07
    جزاء
    0.07
    àn
    0.07
    فاء
    0.07
    Act Density 0.044%

    No Known Activations