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

    Neuronpedia

    INDEX
    Explanations

    segments of continuous whitespace or empty space in code

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

    public private

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.79
    ScopeManager
    -0.77
     IBOutlet
    -0.77
     EClass
    -0.76
    Datuak
    -0.74
     nakalista
    -0.73
    ніципалі
    -0.73
     ddelweddau
    -0.73
    ftagPool
    -0.73
     estekak
    -0.72
    POSITIVE LOGITS
        
    0.62
         
    0.45
            
    0.41
       
    0.40
      
    0.34
           
    0.34
     hormigón
    0.34
                
    0.33
          
    0.33
     kepad
    0.32
    Act Density 0.021%

    No Known Activations