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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron flags the open-class “content” words—mainly nouns and verbs (especially past tense or participle forms)—and remains inactive on the common function words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    秀
    -0.07
     selected
    -0.07
    dr
    -0.07
     coming
    -0.06
    耐
    -0.06
    ZF
    -0.06
    ErrorHandler
    -0.06
    chod
    -0.06
     Bren
    -0.06
    Reaction
    -0.06
    POSITIVE LOGITS
     jylland
    0.07
    ialias
    0.07
     århus
    0.06
    )‏
    0.06
     chambre
    0.06
    три
    0.06
    )은
    0.06
    .addTo
    0.06
    .GetFileName
    0.06
    ยะ
    0.06
    Act Density 0.062%

    No Known Activations