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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash

    This neuron responds to programming-language reserved words and other common code‐syntax tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ITEM
    -0.07
    _CP
    -0.06
    _moves
    -0.06
    기술
    -0.06
    -Class
    -0.06
     daň
    -0.06
    ARRAY
    -0.06
    	session
    -0.06
    _ROUT
    -0.06
    シェ
    -0.06
    POSITIVE LOGITS
     pk
    0.06
     bl
    0.06
     pent
    0.06
     Operational
    0.05
    сы
    0.05
     reckless
    0.05
    ومتر
    0.05
     حالة
    0.05
     odense
    0.05
    unned
    0.05
    Act Density 0.006%

    No Known Activations