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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash

    The neuron detects numeric and quantitative information—numbers, measurements, counts, percentages and other statistical or magnitude expressions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     repaired
    -0.08
     Econ
    -0.07
     Ott
    -0.07
     synchronization
    -0.07
     inflation
    -0.07
     Prevention
    -0.07
     Matters
    -0.07
     Pakistan
    -0.07
     buddies
    -0.07
     biodiversity
    -0.07
    POSITIVE LOGITS
    ホテ
    0.08
    دخ
    0.08
    .Italic
    0.07
    numerusform
    0.07
    �
    0.07
    믈
    0.07
     placer
    0.07
    �
    0.07
    تنظ
    0.06
    �
    0.06
    Act Density 2.966%

    No Known Activations