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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     owed
    -0.08
    Taxes
    -0.07
     Amm
    -0.07
     credits
    -0.07
    作为
    -0.07
     Zeug
    -0.07
    -essential
    -0.07
    kü
    -0.07
    --↵↵
    -0.07
     Ethernet
    -0.07
    POSITIVE LOGITS
     Gaussian
    0.11
     pdf
    0.11
     gaussian
    0.11
    Probability
    0.11
     Probability
    0.10
     probability
    0.10
     Weib
    0.10
    _prob
    0.10
    _pdf
    0.10
     probabilities
    0.10
    Act Density 0.013%

    No Known Activations