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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash

    The neuron fires on JavaScript AJAX‐call syntax—tokens like “data”, “success”, “function” and the surrounding callback structure.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .lucene
    -0.07
    SYM
    -0.07
    scheduler
    -0.06
    ラー
    -0.06
    olulu
    -0.06
    esar
    -0.06
    す
    -0.06
    _student
    -0.06
    找
    -0.06
    ighbor
    -0.06
    POSITIVE LOGITS
     wilderness
    0.08
     financially
    0.07
     ___
    0.07
     rotary
    0.06
     infrastructure
    0.06
    <DateTime
    0.06
     Claim
    0.06
     Missile
    0.06
     Transmit
    0.06
     Hait
    0.06
    Act Density 0.009%

    No Known Activations