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

    Neuronpedia

    INDEX
    Explanations

    structural elements in code, including comments and function definitions

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

    Code-related keywords and symbols

    np_acts-logits-general · gemini-2.0-flash

    keywords and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.73
       
    -0.64
         
    -0.57
        
    -0.56
    ↵
    -0.54
             
    -0.53
           
    -0.52
     
    -0.52
    ↵↵↵
    -0.51
            
    -0.50
    POSITIVE LOGITS
     tslint
    0.79
    noinspection
    0.73
    seamnă
    0.69
     članak
    0.69
    AndEndTag
    0.65
     esterni
    0.64
    [++
    0.64
    !")
    0.63
    endpush
    0.63
     iſt
    0.62
    Act Density 0.090%

    No Known Activations