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

    Neuronpedia

    INDEX
    Explanations

    insert

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of inserting or updating data operations (e.g. “insert” or “update”) in database-related code or questions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    offline
    -0.07
     programm
    -0.07
     proton
    -0.07
     Programm
    -0.07
    	Buffer
    -0.06
     usuario
    -0.06
    	base
    -0.06
     API
    -0.06
    _Code
    -0.06
     protobuf
    -0.06
    POSITIVE LOGITS
     Examiner
    0.07
     práci
    0.06
     bitte
    0.06
     اس
    0.06
     �
    0.06
    San
    0.06
     inspir
    0.06
    dent
    0.06
    خي
    0.06
     Fresh
    0.06
    Act Density 0.017%

    No Known Activations