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

    Neuronpedia

    INDEX
    Explanations

    introductions and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    疗
    -0.06
    .related
    -0.06
     Video
    -0.06
     представ
    -0.06
    UPPORT
    -0.06
    خصوص
    -0.06
     *[
    -0.06
    Marketing
    -0.06
     Brewers
    -0.06
    follow
    -0.06
    POSITIVE LOGITS
    taş
    0.07
    _pot
    0.07
     χρη
    0.06
     правиль
    0.06
     yere
    0.06
    イト
    0.06
     타이
    0.06
    679
    0.06
    别
    0.06
    _probability
    0.06
    Act Density 0.024%

    No Known Activations