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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    This neuron detects property accessor definitions (the “get” and “set” keywords) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical programming/code syntax and tokens, including acronyms, numerals, and structural elements indicative of code snippets or developer logs.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    utive
    -0.06
     amendment
    -0.06
    (Control
    -0.06
    ADA
    -0.06
     soát
    -0.06
    EMON
    -0.06
     EH
    -0.06
     legalized
    -0.06
    _deleted
    -0.06
    -document
    -0.06
    POSITIVE LOGITS
    *'
    0.07
     McInt
    0.07
    unset
    0.06
    653
    0.06
     Queen
    0.06
    ighb
    0.06
     Nvidia
    0.06
    {};↵
    0.06
    rot
    0.06
     mus
    0.06
    Act Density 0.196%

    No Known Activations