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

    Neuronpedia

    INDEX
    Explanations

    common multiples and divisors

    np_max-act · gemini-2.0-flash

    The neuron is triggered by tokens that are decimal‐formatted numbers (floating‐point fractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unavoid
    -0.07
     scales
    -0.06
     kalan
    -0.06
    ``
    -0.06
     uprav
    -0.06
     greedy
    -0.06
    perimental
    -0.06
     SCM
    -0.06
    marvin
    -0.06
    。\
    -0.06
    POSITIVE LOGITS
     celui
    0.07
     نک
    0.06
    .md
    0.06
     gehen
    0.06
    ье
    0.05
     eql
    0.05
     encouragement
    0.05
     plano
    0.05
     المر
    0.05
    	config
    0.05
    Act Density 0.007%

    No Known Activations