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

    Neuronpedia

    INDEX
    Explanations

    complex names and terms typically used in scientific contexts

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

    foreign word fragments

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

    tokens that are proper nouns—names of people, authors, taxa, or other titled entities (e.g., surnames, journal/species names).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.54
    oa̍t
    -0.52
     мәкал
    -0.49
    Personendaten
    -0.47
     propOrder
    -0.42
    s
    -0.41
    i
    -0.39
     createState
    -0.39
    u
    -0.39
     Мексичка
    -0.38
    POSITIVE LOGITS
    tvguidetime
    0.90
     ་་
    0.75
     (\<
    0.74
     ſind
    0.73
     unſ
    0.73
     queſta
    0.72
     Verſ
    0.71
     myſelf
    0.71
     betweenstory
    0.69
    ſcher
    0.68
    Act Density 2.660%

    No Known Activations