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

    Neuronpedia

    INDEX
    Explanations

    numbers and months

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens (numbers, dates, article or section numerals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -webpack
    -0.07
    ieg
    -0.06
    анню
    -0.06
     objectives
    -0.06
    wal
    -0.06
     이어
    -0.06
    /create
    -0.06
    amina
    -0.06
    _repo
    -0.06
    스크
    -0.06
    POSITIVE LOGITS
    ịch
    0.07
     aliqu
    0.07
    graphics
    0.07
    sit
    0.07
     один
    0.06
     dab
    0.06
     Leipzig
    0.06
    ...\
    0.06
    _MAX
    0.06
    .lot
    0.06
    Act Density 0.015%

    No Known Activations