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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numeric tokens (numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     IDE
    -0.06
    =request
    -0.06
     Tal
    -0.06
     Мин
    -0.06
    Bel
    -0.06
    =re
    -0.06
     visita
    -0.06
     Integral
    -0.06
     BinaryTree
    -0.06
     configur
    -0.06
    POSITIVE LOGITS
    เหม
    0.08
    ebo
    0.07
    CEPTION
    0.07
    035
    0.07
    rong
    0.07
    .Cursors
    0.06
     průběhu
    0.06
    rowCount
    0.06
    成
    0.06
    =============↵
    0.06
    Act Density 0.009%

    No Known Activations