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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash

    The neuron is broadly sensitive to short function words—especially common articles and prepositions like “a,” “of,” and “in.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     biom
    -0.07
     polym
    -0.07
     hurt
    -0.06
     ambush
    -0.06
     bran
    -0.06
    jedn
    -0.06
    /games
    -0.06
     wood
    -0.06
    Brun
    -0.06
    answered
    -0.06
    POSITIVE LOGITS
     escorted
    0.07
     THE
    0.07
     самых
    0.06
    ‌اند
    0.06
    вы
    0.06
     Except
    0.06
     dep
    0.06
     />↵↵
    0.06
     it
    0.06
    劇
    0.06
    Act Density 0.069%

    No Known Activations