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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash

    The neuron fires on bits of HTML/XML markup (angle‐bracket tag syntax). It’s detecting opening/closing tag tokens rather than content words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     stalking
    -0.06
    !=
    -0.06
     запах
    -0.06
     кілька
    -0.06
     مرد
    -0.06
    .day
    -0.06
    리카
    -0.06
    odes
    -0.06
     Ruby
    -0.06
     цвета
    -0.06
    POSITIVE LOGITS
    ereal
    0.06
    (Long
    0.06
    :NO
    0.06
    gue
    0.06
    &amp
    0.06
    규
    0.06
     Simply
    0.06
    jam
    0.06
    @Override
    0.06
    .addData
    0.06
    Act Density 0.001%

    No Known Activations