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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "to be" in different contexts and tenses

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

    Tokens before uncommon surnames

    np_acts-logits-general · gemini-2.0-flash

    surnames starting with Has, Is, Les, Kis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Объем
    -0.47
    cule
    -0.46
    XXI
    -0.43
     single
    -0.43
    日閲覧
    -0.43
     oh
    -0.42
    azin
    -0.41
    ACHUSET
    -0.40
     aven
    -0.40
     Farina
    -0.40
    POSITIVE LOGITS
     &___
    0.70
     Himo
    0.67
    thâu
    0.62
    GEBURTSDATUM
    0.59
     AssemblyProduct
    0.59
     Kens
    0.58
    quelles
    0.58
     pinulongan
    0.58
    niająca
    0.57
    انيف
    0.57
    Act Density 0.212%

    No Known Activations