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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron activates on SQL schema elements—table and column identifiers (including punctuation around them) in query definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    риф
    -0.07
    avg
    -0.07
    "C
    -0.07
     земель
    -0.07
     ts
    -0.06
    اطق
    -0.06
     initComponents
    -0.06
     Wan
    -0.06
    Yang
    -0.06
     observers
    -0.06
    POSITIVE LOGITS
     juste
    0.07
    üslüman
    0.07
    (deg
    0.06
    ypo
    0.06
    isión
    0.06
     Зд
    0.06
     při
    0.06
    .RIGHT
    0.06
     DPR
    0.06
    О
    0.06
    Act Density 0.029%

    No Known Activations