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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks in the text

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

    apostrophe or quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enzie
    -0.65
     Maze
    -0.58
     Dive
    -0.56
     }}$}
    -0.55
     bureau
    -0.55
     Freeze
    -0.53
     toile
    -0.53
     Heist
    -0.53
     himo
    -0.53
     Diving
    -0.52
    POSITIVE LOGITS
     ’
    1.33
     '{@
    0.56
    =’
    0.55
     ‘‘
    0.54
     ‘
    0.50
     „
    0.49
    ’’
    0.49
     ‚
    0.48
    0.46
     persoons
    0.46
    Act Density 0.020%

    No Known Activations