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

    Neuronpedia

    INDEX
    Explanations

    rational coefficients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grep
    -0.09
     Twain
    -0.08
     Harvest
    -0.08
    Harvest
    -0.08
    Concurrency
    -0.08
     misl
    -0.08
    Random
    -0.07
     jedhu
    -0.07
     harvest
    -0.07
     Valentine
    -0.07
    POSITIVE LOGITS
     nevertheless
    0.10
     trotzdem
    0.09
     fractions
    0.09
    却
    0.09
     fractional
    0.09
     decimals
    0.09
     atleast
    0.08
     Nevertheless
    0.08
     nonetheless
    0.08
     néanmoins
    0.08
    Act Density 0.031%

    No Known Activations