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

    Neuronpedia

    INDEX
    Explanations

    don't

    np_max-act · gemini-2.0-flash

    C++ functions related to templates and recursion for mathematical operations.

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

    The neuron activates on mentions of recursion, especially tokens like “recursive” or “recursively” describing a function’s recursive behavior.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    819
    -0.07
     rates
    -0.06
     Kickstarter
    -0.06
    LocalStorage
    -0.06
     Gas
    -0.06
     mắt
    -0.06
     угод
    -0.06
     righteous
    -0.06
     Chat
    -0.06
     interviewer
    -0.06
    POSITIVE LOGITS
    _TM
    0.07
     ae
    0.07
    そうな
    0.06
    *y
    0.06
    (binary
    0.06
    ény
    0.06
    >S
    0.06
    /jquery
    0.06
    lix
    0.06
     جدید
    0.06
    Act Density 0.019%

    No Known Activations