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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    statistical data and factual context related to environmental issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on numerical expressions—digits, numbers, measurements, and counts in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ed
    -0.08
    LED
    -0.07
     Friendly
    -0.06
    (split
    -0.06
    де
    -0.06
    /live
    -0.06
     Greek
    -0.06
     εκ
    -0.06
     tz
    -0.06
    yx
    -0.06
    POSITIVE LOGITS
    ٫
    0.07
     emoji
    0.07
     Attr
    0.07
     Ranking
    0.06
    =function
    0.06
    122
    0.06
     "//
    0.06
     thaimassage
    0.06
     MMI
    0.06
    ่าม
    0.06
    Act Density 0.068%

    No Known Activations