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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric dimension values (pixel sizes) in HTML tag attributes (e.g. the numbers in `sizes="WxH"`).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SOUR
    -0.07
     loadData
    -0.07
    Put
    -0.07
    初始化
    -0.06
    .middle
    -0.06
    Apr
    -0.06
     dnů
    -0.06
    "When
    -0.06
    πό
    -0.06
    (sr
    -0.06
    POSITIVE LOGITS
    .Graphics
    0.07
    .Enum
    0.06
    ترك
    0.06
     تط
    0.06
     benz
    0.06
    emploi
    0.06
    ิส
    0.06
     Toe
    0.06
    仁
    0.06
     ech
    0.06
    Act Density 0.003%

    No Known Activations