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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of prefix‐matching on element IDs or attributes (e.g. CSS “[id^=…]” or startsWith calls).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uyễn
    -0.07
    яч
    -0.06
    Boolean
    -0.06
    زان
    -0.06
    Icon
    -0.06
    _xx
    -0.06
     iar
    -0.06
    Щ
    -0.06
     True
    -0.06
    _inventory
    -0.06
    POSITIVE LOGITS
     leftover
    0.08
    参与
    0.07
     نصب
    0.07
     gerçek
    0.07
    给我
    0.07
    猪
    0.06
     bě
    0.06
    istics
    0.06
    quete
    0.06
     τι
    0.06
    Act Density 0.010%

    No Known Activations