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

    Neuronpedia

    INDEX
    Explanations

    references to the term "first" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    first followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.57
    complexContent
    -0.51
    awtextra
    -0.47
    帖最后由
    -0.42
    انجليز
    -0.38
    VYMaps
    -0.38
    RegressionTest
    -0.38
    toMatchSnapshot
    -0.38
    exitRule
    -0.38
    omitempty
    -0.38
    POSITIVE LOGITS
    OGND
    0.48
    First
    0.45
    úgó
    0.43
     fondamentale
    0.42
     ویکی‌پدیا
    0.42
     assin
    0.42
     âmes
    0.41
    MessageOf
    0.41
     المعيارى
    0.41
    first
    0.41
    Act Density 0.075%

    No Known Activations