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

    Neuronpedia

    INDEX
    Explanations

    HTML/XML code

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect HTML/JSX tag syntax, firing on the angle-bracket tokens (“<” and “>”) and the tag names they enclose.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code related to functions and methods in programming.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .mov
    -0.07
    .borrow
    -0.07
     sill
    -0.06
    udicots
    -0.06
     помещ
    -0.06
    �
    -0.06
     �
    -0.06
    .saved
    -0.06
    (animation
    -0.06
    /design
    -0.06
    POSITIVE LOGITS
    ا
    0.07
     Dân
    0.07
    HERE
    0.07
     climate
    0.06
     warranties
    0.06
     happier
    0.06
     نرم
    0.06
    لا
    0.06
     fullName
    0.06
    ICAL
    0.06
    Act Density 0.081%

    No Known Activations