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

    Neuronpedia

    INDEX
    Explanations

    structured lists and outlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    チーム
    0.43
    团队
    0.41
     storytelling
    0.41
     anecd
    0.39
    بانی
    0.39
     팀
    0.38
    encers
    0.38
    اره
    0.38
     barat
    0.38
    acara
    0.38
    POSITIVE LOGITS
              
    0.49
          
    0.45
             
    0.45
               
    0.42
            
    0.41
    дию
    0.41
         
    0.39
                
    0.38
           
    0.37
     Further
    0.37
    Act Density 0.008%

    No Known Activations