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

    Neuronpedia

    INDEX
    Explanations

    ert

    np_max-act · gemini-2.0-flash

    The neuron triggers on tokens that are parts of internal compiler or standard‐library implementation names (e.g. the “Com pc ert” parts of CompCert and “GLIBCXX_MOVE”), i.e. it’s looking for references to such toolchain or library identifiers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /libs
    -0.08
     archived
    -0.07
     canActivate
    -0.06
     accessibility
    -0.06
    operations
    -0.06
     yerleş
    -0.06
    unar
    -0.06
     §§
    -0.06
     پای
    -0.06
     Chem
    -0.06
    POSITIVE LOGITS
     правила
    0.07
     indifferent
    0.06
     FLAGS
    0.06
    __↵↵
    0.06
    &M
    0.06
     которую
    0.06
    影響
    0.06
     Ihrem
    0.06
    legacy
    0.06
    [j
    0.06
    Act Density 0.019%

    No Known Activations