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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to data structures

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

    Code syntax: function, class, struct, etc

    np_acts-logits-general · gemini-2.0-flash

    end of code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astify
    -0.77
    ↵
    -0.69
    دانشنامهٔ
    -0.68
    :
    -0.65
    __':
    -0.65
    ":
    -0.64
     "")
    -0.62
    ':
    -0.62
    \{\\
    -0.58
    HtmlAttribute
    -0.58
    POSITIVE LOGITS
        
    1.16
      
    1.07
       
    1.02
            
    0.97
         
    0.92
          
    0.92
                
    0.91
                                   
    0.91
           
    0.89
              
    0.88
    Act Density 0.168%

    No Known Activations