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

    Neuronpedia

    INDEX
    Explanations

    math concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    booking
    -0.08
    holt
    -0.07
    UIView
    -0.07
     секун
    -0.07
     Leigh
    -0.07
    一句
    -0.07
     suatu
    -0.07
    -one
    -0.07
     feminist
    -0.07
     звон
    -0.07
    POSITIVE LOGITS
    分别
    0.13
     각각
    0.11
     niile
    0.11
     successive
    0.10
     sequential
    0.10
     respectively
    0.09
     arasında
    0.09
     الثلاث
    0.09
     meeste
    0.09
     summarized
    0.09
    Act Density 0.201%

    No Known Activations