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

    Neuronpedia

    INDEX
    Explanations

    comments in code

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

    httphttpsURL in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kanpo
    -0.58
     tugas
    -0.47
     Wellen
    -0.46
     conclusão
    -0.45
     Ergänzung
    -0.45
     chré
    -0.45
     sellado
    -0.43
     Olimp
    -0.43
     Garantía
    -0.42
    expandindo
    -0.42
    POSITIVE LOGITS
     */
    1.14
     */
    0.90
     */
    0.70
      
    0.62
     Fraud
    0.61
     defaultstate
    0.54
    httphttps
    0.54
     ​​
    0.54
     ​
    0.54
     ¬
    0.54
    Act Density 0.009%

    No Known Activations