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

    Neuronpedia

    INDEX
    Explanations

    sections and headings in a document

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

    section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.50
     referrerpolicy
    -0.46
    Autoritní
    -0.44
     Италијани
    -0.43
     AppCompatTheme
    -0.42
     lenker
    -0.42
     autorytatywna
    -0.42
    Билгалдахарш
    -0.40
    RegressionTest
    -0.39
    riwal
    -0.39
    POSITIVE LOGITS
     section
    0.72
     SECTION
    0.65
    Section
    0.64
    \{\\
    0.63
     Section
    0.62
     sections
    0.61
    InSection
    0.61
    UnusedPrivate
    0.59
     sección
    0.59
    section
    0.57
    Act Density 0.001%

    No Known Activations