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

    Neuronpedia

    INDEX
    Explanations

    markup and formatting elements in the text

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

    mr. and mrs. titles

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects HTML/XML-style tags and angle-bracket markup (the "<", ">", and tag boundary tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     surla
    -0.72
    transQ
    -0.71
    WriteTagHelper
    -0.63
     betweenstory
    -0.60
    Filmografia
    -0.59
     snippetHide
    -0.57
    jsxFileName
    -0.55
     StatefulWidget
    -0.55
     NgModule
    -0.54
     defaultstate
    -0.54
    POSITIVE LOGITS
    <bos>
    0.38
    It
    0.35
    !),
    0.34
    cus
    0.33
    ].)
    0.32
    הם
    0.32
     hvem
    0.31
     It
    0.31
    ''',
    0.31
     оно
    0.30
    Act Density 0.007%

    No Known Activations