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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron activates strongly on numeric tokens—particularly dates, docket numbers, and other multi‐digit numerals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    医学
    -0.07
     оно
    -0.07
     headset
    -0.06
     ridic
    -0.06
    /original
    -0.06
     Australia
    -0.06
    了解
    -0.06
    monitor
    -0.06
     raced
    -0.06
    ریز
    -0.06
    POSITIVE LOGITS
    Jessica
    0.07
    {%
    0.06
     $($
    0.06
     hàm
    0.06
     kosten
    0.06
    天
    0.06
     ={↵
    0.06
    _green
    0.06
    ameda
    0.06
     SCI
    0.06
    Act Density 0.004%

    No Known Activations