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

    Neuronpedia

    INDEX
    Explanations

    science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    东风
    -0.07
     doit
    -0.07
    二百
    -0.07
    devices
    -0.07
    (datas
    -0.06
    Users
    -0.06
    .Shared
    -0.06
    优秀
    -0.06
    styled
    -0.06
    .tele
    -0.06
    POSITIVE LOGITS
     ");
    0.08
     hacking
    0.07
    agger
    0.07
     обязательно
    0.06
     Trails
    0.06
     الفند
    0.06
     Retirement
    0.06
    fall
    0.06
     Orange
    0.06
    ORN
    0.06
    Act Density 0.124%

    No Known Activations