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

    Neuronpedia

    INDEX
    Explanations

    database queries and statements

    np_max-act · gemini-2.0-flash

    This neuron flags technical SQL‐ and query‐related tokens (e.g. “SQL,” “query,” “queries,” “statements”) in code or configuration contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Topics
    -0.07
     schools
    -0.06
     граф
    -0.06
     фунда
    -0.06
     Syria
    -0.06
    Targets
    -0.06
    	block
    -0.06
     Dart
    -0.06
    782
    -0.06
     copied
    -0.06
    POSITIVE LOGITS
     jasmine
    0.06
    -sem
    0.06
    _cov
    0.06
    -)
    0.06
    	Response
    0.06
    adds
    0.06
    -how
    0.06
    christ
    0.06
     Nhà
    0.06
    metic
    0.06
    Act Density 0.040%

    No Known Activations