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

    Neuronpedia

    INDEX
    Explanations

    ">"

    np_max-act · gemini-2.0-flash

    programming-related terminology and function definitions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on HTML/XML-like markup tags (e.g. `<div>`, `<span>`, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Rounds
    -0.06
     commitment
    -0.06
    _rom
    -0.06
    Constructed
    -0.06
     Excellence
    -0.06
     pride
    -0.06
     Inch
    -0.06
    thing
    -0.06
    ertainty
    -0.06
    (expected
    -0.06
    POSITIVE LOGITS
     jumlah
    0.06
    .split
    0.06
    ided
    0.06
    reatest
    0.06
     fashionable
    0.06
    ouser
    0.06
     ENTER
    0.06
    静
    0.06
     maxLength
    0.06
     сіль
    0.06
    Act Density 0.003%

    No Known Activations