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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron detects list or outline markers and section numbering (e.g., numeric item prefixes like “1)”, colons introducing lists, and similar enumeration tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ticker
    -0.07
     rinse
    -0.07
     reckon
    -0.06
    评论
    -0.06
     dipped
    -0.06
    Van
    -0.06
     CATEGORY
    -0.06
    "On
    -0.06
    MAT
    -0.06
     vak
    -0.06
    POSITIVE LOGITS
    ุร
    0.07
     Guidelines
    0.07
     exist
    0.07
    -ext
    0.07
    รว
    0.07
     advertis
    0.06
     Pest
    0.06
    orr
    0.06
     вищ
    0.06
    destruct
    0.06
    Act Density 0.038%

    No Known Activations