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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash

    This neuron fires on common Spanish-language function words (articles, prepositions, conjunctions), effectively marking spans of Spanish text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    akh
    -0.06
     fry
    -0.06
     unh
    -0.06
    alls
    -0.06
     spo
    -0.06
    DW
    -0.06
     lai
    -0.06
    LAN
    -0.06
     marathon
    -0.06
    recommend
    -0.06
    POSITIVE LOGITS
     назад
    0.07
     электр
    0.07
    >".$
    0.06
    ']}
    0.06
     بل
    0.06
    0.06
     exclude
    0.06
     QtGui
    0.06
     mediaPlayer
    0.06
     구글상위
    0.06
    Act Density 0.297%

    No Known Activations