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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects HTML table cell tags (e.g., `<td>` and `<th>`) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    :@"%@",
    -0.07
     ترین
    -0.07
     많이
    -0.06
    HomeAs
    -0.06
    ("/",
    -0.06
    .MixedReality
    -0.06
    ++,
    -0.06
    .;.;.;.;
    -0.06
     focused
    -0.06
    を
    -0.06
    POSITIVE LOGITS
     coronavirus
    0.07
     {↵↵
    0.06
     atd
    0.06
     liaison
    0.06
     віднов
    0.06
     Outreach
    0.06
    inee
    0.06
    rad
    0.06
    ["
    0.06
    istance
    0.06
    Act Density 0.016%

    No Known Activations