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

    Neuronpedia

    INDEX
    Explanations

    ori

    np_max-act · gemini-2.0-flash

    This neuron selectively detects specialized technical or scientific terminology.

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

    terms that are domain-specific or technical (often proper nouns, acronyms, or specialized nouns)

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    .abort
    -0.07
    (My
    -0.06
     dél
    -0.06
    ://{
    -0.06
    _APPLICATION
    -0.06
     east
    -0.06
     muh
    -0.06
     Lis
    -0.06
    |↵↵
    -0.06
    iet
    -0.06
    POSITIVE LOGITS
    oundingBox
    0.07
     retirees
    0.06
    _trigger
    0.06
     Wonderland
    0.06
    urved
    0.06
    lendirme
    0.06
     orderly
    0.06
    _Syntax
    0.06
     lurking
    0.06
    +-+-+-+-
    0.06
    Act Density 0.569%

    No Known Activations