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

    Neuronpedia

    INDEX
    Explanations

    BOOST

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on occurrences of the uppercase identifier “BOOST” (as used in Boost-library include guards and macro names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ेव
    -0.06
    dato
    -0.06
     bru
    -0.06
    klady
    -0.06
    vars
    -0.06
    okrat
    -0.06
    لح
    -0.06
    plib
    -0.06
    ,k
    -0.06
    _eg
    -0.06
    POSITIVE LOGITS
     تر
    0.06
     Future
    0.06
     vigorously
    0.06
    にする
    0.06
     Đặc
    0.06
     Glas
    0.06
     تعد
    0.06
     chronic
    0.06
     accomplished
    0.06
    (moment
    0.06
    Act Density 0.001%

    No Known Activations