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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical references within the text

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

    Years in the 1800s, 1900s, 2000s

    np_acts-logits-general · gemini-2.0-flash

    years or ranges of years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nothing
    -0.69
    Nothing
    -0.67
     nada
    -0.66
    nothing
    -0.66
     Nothing
    -0.64
     NOTHING
    -0.59
     OMITBAD
    -0.59
    WaitGroup
    -0.56
     nothin
    -0.55
     autorytatywna
    -0.54
    POSITIVE LOGITS
    ंदीखरीदारी
    0.61
    ostante
    0.61
     Exacts
    0.59
     Trouver
    0.56
     <>",
    0.54
    audiovisuel
    0.52
    DataAnnotations
    0.52
    ustice
    0.51
    deau
    0.50
     CURIAM
    0.50
    Act Density 0.542%

    No Known Activations