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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs and API-related keywords

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

    macro definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.44
     nearly
    -0.43
          
    -0.35
       
    -0.35
        
    -0.35
    -0.35
    Leftrightarrow
    -0.35
     Real
    -0.34
                
    -0.34
     almost
    -0.34
    POSITIVE LOGITS
    stateMutability
    0.71
     pinulongan
    0.70
     betweenstory
    0.67
    majánló
    0.66
     nonUne
    0.62
     concierge
    0.61
     vixion
    0.60
     concier
    0.59
    ſcher
    0.58
     ſes
    0.57
    Act Density 0.007%

    No Known Activations