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

    Neuronpedia

    INDEX
    Explanations

    `[:`

    np_max-act · gemini-2.0-flash

    The neuron fires on Neo4j relationship type tokens (e.g. the `[:HAS_…]` or `[:PUBLISHED_IN_YEAR]` parts), i.e. it detects relationship declarations or references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -Qaeda
    -0.07
     Temple
    -0.07
    -K
    -0.06
    .isDirectory
    -0.06
     WTO
    -0.06
    (artist
    -0.06
     maintenant
    -0.06
     temple
    -0.06
    -op
    -0.06
    ו�
    -0.06
    POSITIVE LOGITS
     itk
    0.08
    ản
    0.07
     существ
    0.06
     FILES
    0.06
    aternion
    0.06
    179
    0.06
     Features
    0.06
    	stat
    0.06
    _recall
    0.06
     �
    0.06
    Act Density 0.003%

    No Known Activations