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

    Neuronpedia

    INDEX
    Explanations

    defining describing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    罴
    -0.08
    펭
    -0.07
     الصفحة
    -0.07
    ihu
    -0.07
     Mang
    -0.07
    essages
    -0.07
    .paginator
    -0.07
    uname
    -0.07
     subpo
    -0.07
    browse
    -0.07
    POSITIVE LOGITS
     jewellery
    0.07
    がかか
    0.07
    처럼
    0.07
     city
    0.06
    cir
    0.06
    三亚
    0.06
     tastes
    0.06
    _heads
    0.06
     northeast
    0.06
     coral
    0.06
    Act Density 0.077%

    No Known Activations