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

    Neuronpedia

    INDEX
    Explanations

    HTML tag start

    np_max-act · gemini-2.0-flash

    This neuron activates on the “<!” token, i.e. the start of HTML/XML declarations or comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -0.07
    perienced
    -0.07
    illisecond
    -0.06
     Formal
    -0.06
    amilies
    -0.06
     fences
    -0.06
     Profile
    -0.06
    -0.06
    -0.06
     Nguyên
    -0.06
    POSITIVE LOGITS
    <!
    0.11
     आपक
    0.08
     cgi
    0.07
    kening
    0.07
    @extends
    0.06
     eius
    0.06
    sie
    0.06
    inations
    0.06
    .dat
    0.06
    uento
    0.06
    Act Density 0.001%

    No Known Activations