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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities, particularly names and organizations

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

    names and associated words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.67
    GEBURTSDATUM
    -0.63
    Diweddarwch
    -0.58
    Попис
    -0.57
     linkovi
    -0.56
    sizeCache
    -0.54
    verwijspagina
    -0.51
     disambiguazione
    -0.51
     ffilmiau
    -0.50
     rhestr
    -0.50
    POSITIVE LOGITS
    Numerade
    0.38
     Joseph
    0.38
     Joe
    0.38
    これだけ
    0.37
     SimpleName
    0.36
     Wilson
    0.35
    toBe
    0.35
     Smith
    0.35
    UnknownFieldSet
    0.35
     John
    0.34
    Act Density 0.023%

    No Known Activations