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

    Neuronpedia

    INDEX
    Explanations

    sections of the text with no significant data or content

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

    Code, questions, and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    bash script starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.87
     AssemblyCulture
    -0.80
     disambiguazione
    -0.75
    WithIOException
    -0.67
    (__('
    -0.65
    WebVitals
    -0.64
     виправивши
    -0.64
    spesies
    -0.62
    脚注の使い方
    -0.62
    Rhestr
    -0.62
    POSITIVE LOGITS
    <eos>
    1.21
    </tr>
    0.94
    [toxicity=0]
    0.92
        
    0.90
    ↵↵
    0.82
    ↵↵↵↵↵
    0.80
      
    0.76
            
    0.76
    ↵↵↵↵
    0.74
    ↵↵↵↵↵↵
    0.74
    Act Density 0.093%

    No Known Activations