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

    Neuronpedia

    INDEX
    Explanations

    end of section or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
             
    0.41
       
    0.38
            
    0.37
         
    0.34
        
    0.34
              
    0.34
           
    0.33
     exists
    0.33
          
    0.33
                    
    0.33
    POSITIVE LOGITS
     murderous
    0.44
     помочь
    0.42
    пси
    0.40
    밌
    0.40
    𝔪
    0.39
     काल्पनिक
    0.39
     dast
    0.39
     fict
    0.38
    بعض
    0.38
    揾
    0.38
    Act Density 2.065%

    No Known Activations