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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gemini-2.0-flash

    words with specific suffixes or prefixes

    np_token-act-pair-logits · gpt-4o-mini

    Dates and times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EndGlobalSection
    -0.85
     تضيفلها
    -0.84
    Geplaatst
    -0.82
    ########.
    -0.72
    Демографія
    -0.72
    contentLoaded
    -0.71
    httphttps
    -0.67
    IsContent
    -0.67
     AspNetCore
    -0.66
     للمعارف
    -0.65
    POSITIVE LOGITS
    Parcelize
    0.50
     Cuer
    0.48
    fulness
    0.45
    hos
    0.45
    τιά
    0.43
     irons
    0.42
     Kinders
    0.42
     Walkover
    0.42
    CrossRef
    0.41
    ITO
    0.41
    Act Density 3.735%

    No Known Activations