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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash

    concepts related to object-oriented programming and data structures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to mentions of programming‐language entity declarations, e.g. type names like “class,” “array,” or “module.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ुई
    -0.07
    tips
    -0.06
    LOCKS
    -0.06
     Quote
    -0.06
    zens
    -0.06
    hab
    -0.06
    exec
    -0.06
    Protection
    -0.06
     penalty
    -0.06
     Shoes
    -0.06
    POSITIVE LOGITS
     Whole
    0.07
     trẻ
    0.06
    <class
    0.06
     tö
    0.06
    _like
    0.06
    高校
    0.06
    ")
↵
    0.06
    //**↵
    0.06
     Но
    0.06
    .echo
    0.06
    Act Density 0.071%

    No Known Activations