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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recycl
    -0.08
    .:.
    -0.06
    (robot
    -0.06
     <!--[
    -0.06
    胶
    -0.06
     א
    -0.06
     Pierre
    -0.06
    bout
    -0.06
     mate
    -0.06
    звичай
    -0.06
    POSITIVE LOGITS
     трав
    0.06
    ológ
    0.06
    新闻
    0.06
    ах
    0.06
     temporada
    0.06
     vý
    0.06
     Inside
    0.06
    ossed
    0.06
    egis
    0.06
    झ
    0.06
    Act Density 0.008%

    No Known Activations