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

    Neuronpedia

    INDEX
    Explanations

    graduate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pul
    -0.07
     comed
    -0.07
    _unix
    -0.07
     결혼
    -0.07
    یان
    -0.07
    頻
    -0.06
    簡
    -0.06
     سرعت
    -0.06
     закон
    -0.06
     Clown
    -0.06
    POSITIVE LOGITS
    args
    0.07
     представ
    0.07
    others
    0.07
    ９
    0.06
     gt
    0.06
    しく
    0.06
     args
    0.06
     Alexander
    0.06
    EventArgs
    0.06
     depend
    0.06
    Act Density 0.001%

    No Known Activations