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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash

    The neuron detects SQL conditional expressions, i.e. the “CASE WHEN … END” constructs used inside queries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Durant
    -0.08
     glac
    -0.07
     ciz
    -0.06
    iegel
    -0.06
     ря
    -0.06
    ocular
    -0.06
     taraf
    -0.06
    =");↵
    -0.06
    /map
    -0.06
    آ
    -0.06
    POSITIVE LOGITS
    다
    0.07
     deter
    0.06
    τιο
    0.06
    _dl
    0.06
    λεκ
    0.06
     Holds
    0.06
    	Runtime
    0.06
     윤
    0.06
    anine
    0.06
    يدة
    0.06
    Act Density 0.004%

    No Known Activations