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

    Neuronpedia

    INDEX
    Explanations

    st

    np_max-act · gemini-2.0-flash

    The neuron fires on the special “start”/“end” header ID markers (e.g. `<|start_header_id|>` and `<|end_header_id|>`) that bracket metadata sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    text in languages other than English, especially tokens with diacritics or non‑Latin Unicode characters.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    itemId
    -0.08
    AccessType
    -0.07
    �
    -0.07
    ốt
    -0.07
     вір
    -0.07
    ONG
    -0.07
    .TableName
    -0.07
     Scott
    -0.07
    ожет
    -0.07
     حرکت
    -0.07
    POSITIVE LOGITS
    ,''
    0.08
     erv
    0.07
    ''
    0.06
    ฤด
    0.06
    .""
    0.06
    ‎
    0.06
    .''
    0.06
    ��
    0.06
     ary
    0.06
    CDATA
    0.06
    Act Density 35.625%

    No Known Activations