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

    Neuronpedia

    INDEX
    Explanations

    statistics and percentages

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric-statistical tokens (numbers, percentages, measurements) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     suburban
    -0.07
    .Orders
    -0.06
     گونه
    -0.06
     MOCK
    -0.06
    781
    -0.06
    .Qual
    -0.06
    )\↵
    -0.06
     component
    -0.06
     piracy
    -0.06
    @testable
    -0.06
    POSITIVE LOGITS
    лаб
    0.07
    .ToArray
    0.07
    called
    0.07
    -'.$
    0.07
    lier
    0.06
    μως
    0.06
    豆
    0.06
    ánd
    0.06
    搜索
    0.06
    nb
    0.06
    Act Density 0.111%

    No Known Activations