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

    Neuronpedia

    INDEX
    Explanations

    the conclusion or closure in a given context

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

    "<end_of_turn>"

    np_acts-logits-general · gemini-2.0-flash

    Wikipedia pages

    np_acts-logits-general · gemini-2.5-flash-lite

    end-of-turn conversation boundary markers.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     and
    -0.63
     or
    -0.60
    }{*}{
    -0.57
    ,
    -0.57
    -
    -0.54
    VIAF
    -0.46
     of
    -0.45
     &
    -0.44
      
    -0.43
     car
    -0.42
    POSITIVE LOGITS
     Wikiseite
    0.69
     disambiguazione
    0.68
    ResumeLayout
    0.63
    bibfield
    0.60
     itſelf
    0.59
     ostavi
    0.58
    pecabe
    0.57
     Audiodateien
    0.56
    endpush
    0.55
    Personensuche
    0.55
    Act Density 0.806%

    No Known Activations