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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash

    This neuron fires on the article’s headword or main entry term—especially when it’s a non-English or transliterated name at the start of the entry.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    童
    -0.07
    신청
    -0.07
    cury
    -0.07
     окруж
    -0.07
     gospel
    -0.07
    written
    -0.06
     flu
    -0.06
    .xml
    -0.06
     Skyl
    -0.06
     determine
    -0.06
    POSITIVE LOGITS
    (cert
    0.06
    /Web
    0.06
     everything
    0.06
    ????????????????
    0.06
     serait
    0.06
    ィ
    0.06
     обов
    0.06
    ,['
    0.06
    ENCIES
    0.06
    -oper
    0.06
    Act Density 0.031%

    No Known Activations