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

    Neuronpedia

    INDEX
    Explanations

    binomial distributions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deterg
    -0.09
    ensive
    -0.09
    gest
    -0.09
     방향
    -0.08
    깨
    -0.08
     곳
    -0.08
     oxide
    -0.08
     våre
    -0.08
     detergent
    -0.08
    Disposable
    -0.08
    POSITIVE LOGITS
     probabilities
    0.14
     factorial
    0.12
     bin
    0.11
     probability
    0.11
    bin
    0.11
    概率
    0.10
     Probability
    0.09
     tail
    0.09
     Bin
    0.09
    _probability
    0.09
    Act Density 0.020%

    No Known Activations