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

    Neuronpedia

    INDEX
    Explanations

    references to taking time off or breaks

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

    days off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.50
    ksom
    -0.47
     Zwie
    -0.42
     queima
    -0.41
     обстанов
    -0.39
     campes
    -0.38
     кня
    -0.38
     alfombra
    -0.38
    makeConstraints
    -0.38
     tæ
    -0.37
    POSITIVE LOGITS
    Personensuche
    0.55
    休日
    0.54
    Weekend
    0.52
     weekends
    0.52
    Portail
    0.51
    itespace
    0.50
     OFDb
    0.49
     nghỉ
    0.49
    abetes
    0.48
    yntaxException
    0.48
    Act Density 0.004%

    No Known Activations