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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash

    The neuron activates on XML/HTML‐style tag tokens (the angle‐bracketed element names and delimiters).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     receivers
    -0.06
     Haus
    -0.06
     Spit
    -0.06
     Ví
    -0.06
     Es
    -0.06
     Mec
    -0.06
    ervoir
    -0.06
     hướng
    -0.06
     xx
    -0.06
    arium
    -0.06
    POSITIVE LOGITS
    ﾞﾞ
    0.07
     guerra
    0.06
    (IEnumerable
    0.06
     Blogger
    0.06
    ending
    0.06
     času
    0.06
     asp
    0.06
     XHTML
    0.06
    ическая
    0.06
    Linked
    0.06
    Act Density 0.018%

    No Known Activations