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

    Neuronpedia

    INDEX
    Explanations

    Time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    这也是
    -0.07
    (WebDriver
    -0.07
     hamburger
    -0.07
    _have
    -0.07
     Hiệp
    -0.07
     intptr
    -0.06
    ቐ
    -0.06
     данной
    -0.06
     hosting
    -0.06
     dengan
    -0.06
    POSITIVE LOGITS
    utherford
    0.07
     neutral
    0.07
    要不然
    0.07
     зам
    0.07
     Lois
    0.07
     Vote
    0.07
     glued
    0.07
    ::::::::
    0.07
     fourteen
    0.07
    ерж
    0.07
    Act Density 0.076%

    No Known Activations