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

    Neuronpedia

    INDEX
    Explanations

    references to administrative processes and terminology

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

    Followed by a definite or possessive article

    np_acts-logits-general · gemini-2.0-flash

    determiners and common nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.80
     Réponses
    -0.73
     esternos
    -0.69
     ་་
    -0.68
    verwijspagina
    -0.68
    RectangleBorder
    -0.67
    Cyfeiriadau
    -0.65
     raiſ
    -0.62
     externi
    -0.61
     Wikispecies
    -0.60
    POSITIVE LOGITS
     the
    1.24
     them
    1.18
     their
    1.12
     some
    1.10
     your
    1.02
     him
    0.98
     a
    0.92
     an
    0.91
     his
    0.91
     its
    0.88
    Act Density 0.718%

    No Known Activations