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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (integer or floating‐point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     STILL
    -0.07
    浴
    -0.06
     no
    -0.06
     текст
    -0.06
     язы
    -0.06
    ض
    -0.06
     Cars
    -0.06
    .JSON
    -0.06
     Really
    -0.06
    "data
    -0.06
    POSITIVE LOGITS
     breakthrough
    0.07
    }-{
    0.06
    -dr
    0.06
    Recipient
    0.06
     absolute
    0.06
    _polygon
    0.06
    txn
    0.06
    ündeki
    0.06
     endPoint
    0.06
    -seat
    0.06
    Act Density 0.019%

    No Known Activations