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

    Neuronpedia

    INDEX
    Explanations

    Math punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Observe
    -0.09
    Idea
    -0.09
    ，但是
    -0.09
     wish
    -0.08
    但是
    -0.08
    Usually
    -0.08
     Maybe
    -0.08
    Maybe
    -0.08
    ENCES
    -0.08
     مشهور
    -0.08
    POSITIVE LOGITS
     hesap
    0.13
     totals
    0.13
     계산
    0.13
     calculation
    0.12
     गण
    0.12
    .total
    0.12
     calculated
    0.12
     calculations
    0.12
    .calculate
    0.12
     Calculates
    0.11
    Act Density 0.078%

    No Known Activations