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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash

    The neuron activates on metadata field names in a document’s front-matter (e.g. tokens like “id,” “translation,” “loc” as used in keys such as ms.asset.id, ms.translation, ms.loc.file.id).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     zf
    -0.07
    (cube
    -0.07
    ывая
    -0.06
     são
    -0.06
    หาย
    -0.06
    Ban
    -0.06
    .field
    -0.06
     〜
    -0.06
    dın
    -0.06
     Bed
    -0.06
    POSITIVE LOGITS
    _cid
    0.07
    id
    0.07
    .LogInformation
    0.06
    Discover
    0.06
    richt
    0.06
    _CITY
    0.06
    iloc
    0.06
    512
    0.06
     discriminate
    0.06
    _PER
    0.06
    Act Density 0.000%

    No Known Activations