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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hell
    -0.07
    strate
    -0.07
    [@"
    -0.07
    ática
    -0.06
     imdb
    -0.06
    іє
    -0.06
    -ever
    -0.06
     asserts
    -0.06
     ад
    -0.06
    ало
    -0.06
    POSITIVE LOGITS
    isplay
    0.07
    는지
    0.06
    ,l
    0.06
    creativecommons
    0.06
    MinMax
    0.06
    .quick
    0.06
    ۵۰
    0.06
    SX
    0.06
     عقد
    0.06
     شو
    0.06
    Act Density 0.091%

    No Known Activations