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

    Neuronpedia

    INDEX
    Explanations

    android

    np_max-act · gemini-2.0-flash

    This neuron detects XML attribute names in Android layout files, specifically tokens using the “android:” namespace prefix.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    　　　 　
    -0.07
    .JPG
    -0.07
     الموقع
    -0.06
     همیشه
    -0.06
     نوشته
    -0.06
    _capacity
    -0.06
    pathname
    -0.06
     팔
    -0.06
    ευση
    -0.06
     Undefined
    -0.06
    POSITIVE LOGITS
    وو
    0.07
    306
    0.06
     Appet
    0.06
     ruta
    0.06
     بور
    0.06
     itk
    0.06
     FB
    0.06
    ='',↵
    0.06
    .pb
    0.06
    Self
    0.06
    Act Density 0.006%

    No Known Activations