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

    Neuronpedia

    INDEX
    Explanations

    punctuation and "the"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Metric
    -0.09
    Metrics
    -0.09
    .metrics
    -0.08
    .XPath
    -0.08
     metric
    -0.08
     circuitry
    -0.08
     metrics
    -0.08
     tect
    -0.08
    Wave
    -0.08
     calculus
    -0.07
    POSITIVE LOGITS
     최대
    0.10
     ادب
    0.09
    vereiro
    0.09
     سنة
    0.09
     最大
    0.08
     banned
    0.08
     abide
    0.08
     максимально
    0.08
    "))↵
    0.08
     عرب
    0.08
    Act Density 0.003%

    No Known Activations