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

    Neuronpedia

    INDEX
    Explanations

    user presence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Нау
    0.55
    ر
    0.54
    س
    0.48
    ל
    0.46
    ك
    0.46
    ز
    0.45
    ए
    0.44
    Са
    0.44
    Kết
    0.44
    Цент
    0.43
    POSITIVE LOGITS
     user
    0.76
     User
    0.65
    ByUser
    0.64
    User
    0.61
     用户
    0.61
     USER
    0.59
     setUser
    0.58
     getUser
    0.58
     यूजर
    0.57
    USER
    0.56
    Act Density 0.041%

    No Known Activations