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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron detects the (“is”) in patent figure‐reference statements—i.e. the “is” in phrases like “FIG. 1 is …”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     emissions
    -0.06
     HG
    -0.06
    cba
    -0.06
     Gö
    -0.06
    -0.06
    _SUPPORT
    -0.06
     purity
    -0.06
     harvesting
    -0.06
     juni
    -0.06
    Stop
    -0.06
    POSITIVE LOGITS
    .gallery
    0.08
    ?>"↵
    0.07
     underwater
    0.07
     jedis
    0.06
    0.06
     Princeton
    0.06
    CppClass
    0.06
    и
    0.06
    ジ
    0.06
    ательных
    0.06
    Act Density 0.002%

    No Known Activations