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

    Neuronpedia

    INDEX
    Explanations

    Y

    np_max-act · gemini-2.0-flash

    academic references and citations in research texts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is detect HTML/XML markup tags (e.g. `<p>`, `<br>`, `</p>`, links, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     kon
    -0.07
    Coverage
    -0.07
     Rick
    -0.07
    .bn
    -0.07
    ![
    -0.06
    atted
    -0.06
     Coverage
    -0.06
    arring
    -0.06
     scn
    -0.06
     tents
    -0.06
    POSITIVE LOGITS
    -ext
    0.07
    _extra
    0.06
     Arkansas
    0.06
    _ident
    0.06
     CHO
    0.06
     extraordin
    0.06
    (strtolower
    0.06
     worthwhile
    0.06
    Cross
    0.06
    .constructor
    0.06
    Act Density 0.032%

    No Known Activations