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

    Neuronpedia

    INDEX
    Explanations

    elements related to LaTeX document structure and formatting

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

    LaTeX document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.98
    Manbalar
    -0.98
    ésultats
    -0.94
    <unused68>
    -0.92
    <unused41>
    -0.92
    <unused23>
    -0.91
    <unused52>
    -0.91
    <unused8>
    -0.91
    <unused74>
    -0.91
    [@BOS@]
    -0.91
    POSITIVE LOGITS
    documentclass
    0.67
    ↵
    0.40
            
    0.37
    '
    0.36
        
    0.35
    4
    0.34
          
    0.33
      
    0.33
    1
    0.33
    -
    0.32
    Act Density 0.002%

    No Known Activations