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

    Neuronpedia

    INDEX
    Explanations

    _HAS

    np_max-act · gemini-2.0-flash

    This neuron fires on C/C++ preprocessor macro names and conditional‐compilation identifiers (e.g. BOOST_* macros in #if/defined checks).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .oracle
    -0.07
     sein
    -0.06
    Corner
    -0.06
    prite
    -0.06
     payout
    -0.06
     stains
    -0.06
    media
    -0.06
    ottes
    -0.06
     -*
    -0.06
    .partner
    -0.06
    POSITIVE LOGITS
    ดร
    0.07
    алення
    0.07
     simultaneously
    0.07
    _filepath
    0.07
    قل
    0.07
    바
    0.06
     خشک
    0.06
     ranging
    0.06
    成
    0.06
    cess
    0.06
    Act Density 0.002%

    No Known Activations