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

    Neuronpedia

    INDEX
    Explanations

    common denominators

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens (multi‐digit numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     '-'
    -0.07
    .mon
    -0.07
    tep
    -0.06
    INUE
    -0.06
    puted
    -0.06
    pués
    -0.06
     eben
    -0.06
     Nero
    -0.06
    _Show
    -0.06
     خشک
    -0.06
    POSITIVE LOGITS
     Marlins
    0.06
     societies
    0.06
    <div
    0.06
     senator
    0.06
    continent
    0.06
    şehir
    0.06
    $content
    0.06
     Latinos
    0.06
     whites
    0.06
    /pl
    0.06
    Act Density 0.002%

    No Known Activations