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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, particularly recent or past events

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

    Time periods following "past" or "last."

    np_acts-logits-general · gemini-2.0-flash

    past/last time periods quantified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.89
     فريبيس
    -0.75
     صوتيه
    -0.75
    rrggbb
    -0.74
     незавершена
    -0.73
    webElementXpaths
    -0.66
    Personensuche
    -0.65
    原始内容存档于
    -0.64
     Италијани
    -0.63
     跳转至
    -0.61
    POSITIVE LOGITS
     few
    1.90
     couple
    1.46
    few
    1.40
     two
    1.22
    Few
    1.21
     Few
    1.18
     FEW
    1.15
     handful
    1.15
     several
    1.12
     dozen
    1.09
    Act Density 0.198%

    No Known Activations