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

    Neuronpedia

    INDEX
    Explanations

    the start of new sections or breaks in the text

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

    Followed by certain punctuation or the word "The"

    np_acts-logits-general · gemini-2.0-flash

    loanfreeSimpsondollarorthe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -1.04
    ,
    -1.01
    .
    -1.00
     
    -0.95
     “
    -0.90
     and
    -0.87
     ‘
    -0.84
     to
    -0.82
     "
    -0.81
     in
    -0.80
    POSITIVE LOGITS
     يتيمه
    1.84
     ſind
    1.59
     ―――――
    1.57
     незавершена
    1.56
     iſt
    1.56
    DockStyle
    1.56
    ^(@)
    1.55
     المعيارى
    1.53
     houſe
    1.50
    GEBURTSDATUM
    1.46
    Act Density 0.019%

    No Known Activations