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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their arrangement in text

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

    Colon followed by a common word

    np_acts-logits-general · gemini-2.0-flash

    updates and fixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -1.05
    tagext
    -1.01
     незавершена
    -1.00
    ValueStyle
    -0.94
     المعيارى
    -0.94
    abestanden
    -0.94
    enumi
    -0.93
    parsedMessage
    -0.87
     سكانية
    -0.86
    enumii
    -0.85
    POSITIVE LOGITS
     
    0.87
     The
    0.80
      
    0.79
    :
    0.78
     A
    0.76
    ↵
    0.75
     L
    0.63
    ↵↵
    0.62
     If
    0.60
     (
    0.60
    Act Density 0.508%

    No Known Activations