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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Powered
    -0.06
    BundleOrNil
    -0.06
     ederek
    -0.06
    zę
    -0.06
     初始化
    -0.06
    상담
    -0.06
    brand
    -0.06
     UserDao
    -0.06
    _ptrs
    -0.06
     authored
    -0.06
    POSITIVE LOGITS
    [@
    0.07
     жал
    0.06
     Austin
    0.06
     после
    0.06
    Body
    0.06
    (sid
    0.06
     永
    0.06
    ookie
    0.06
     dive
    0.06
    uego
    0.06
    Act Density 0.051%

    No Known Activations