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

    Neuronpedia

    INDEX
    Explanations

    terms related to classifications or categories within structured data

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

    after "of" (or similar prepositions)

    np_acts-logits-general · gemini-2.0-flash

    enumerating instances or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.59
     âmes
    -0.58
     épaules
    -0.52
     vérit
    -0.51
     rigue
    -0.50
     lèvres
    -0.48
     pères
    -0.48
     inconvénients
    -0.46
     dieux
    -0.46
     leçons
    -0.45
    POSITIVE LOGITS
     usernames
    0.59
     occurrences
    0.59
     orientations
    0.58
     setups
    0.57
     editions
    0.57
     newsletters
    0.56
     scanners
    0.55
    ocations
    0.54
     instances
    0.54
     backups
    0.54
    Act Density 0.651%

    No Known Activations