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

    Neuronpedia

    INDEX
    Explanations

    file path syntax

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

    system executable paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geſch
    -0.77
     Geiſt
    -0.74
     Geſch
    -0.74
    majánló
    -0.73
    enablog
    -0.72
    iſchen
    -0.70
     queſta
    -0.69
    ésultats
    -0.69
    ſſung
    -0.68
     laſſen
    -0.67
    POSITIVE LOGITS
      
    0.49
    
    0.43
    complexContent
    0.42
       
    0.40
          
    0.40
    ]
    0.39
    0.38
     an
    0.38
    </em>
    0.38
                
    0.38
    Act Density 0.001%

    No Known Activations