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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in text

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

    Quotation marks and apostrophes

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.84
     Feu
    -0.79
    kháu
    -0.76
     Hein
    -0.73
     pend
    -0.70
     Pich
    -0.69
     Pols
    -0.69
    ്ട
    -0.69
    SequentialGroup
    -0.69
    fă
    -0.67
    POSITIVE LOGITS
    、“
    1.21
    .’”
    1.18
    ’
    1.12
    ,’”
    1.09
    ’:
    1.07
    ’.”
    1.06
    ’,
    1.04
    ’.
    1.03
    ’”
    1.02
    ,’
    1.02
    Act Density 0.389%

    No Known Activations