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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence-ending indicators

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    Mawhinney

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "):
    -0.74
    "],
    -0.69
     }}"></
    -0.68
    неопр
    -0.66
     =
    -0.65
     =>
    -0.64
    +'</
    -0.64
    }_\
    -0.64
    *',
    -0.63
    '):
    -0.62
    POSITIVE LOGITS
      
    1.71
       
    1.11
     ​​
    1.07
    　
    0.92
        
    0.81
      
    0.74
    Jîn
    0.57
    ynchronously
    0.55
    DoubleQuotes
    0.55
     HttpNotFound
    0.54
    Act Density 0.352%

    No Known Activations