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

    Neuronpedia

    INDEX
    Explanations

    paragraphs or sections formatted with consistent indentation or markers

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

    option("password", "cloudera")

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.96
     queſta
    -0.90
     XNUMX
    -0.89
    ThroughAttribute
    -0.89
     faſt
    -0.88
    ſſung
    -0.87
     ſta
    -0.85
    mpagne
    -0.83
    يكب
    -0.83
    -0.82
    POSITIVE LOGITS
             
    1.17
            
    0.92
              
    0.90
                     
    0.84
                 
    0.83
    0.82
                             
    0.82
               
    0.79
                            
    0.79
           
    0.78
    Act Density 0.033%

    No Known Activations