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

    Neuronpedia

    INDEX
    Explanations

    Python code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ჯგუფი
    0.49
    ₲
    0.47
    ⼈
    0.47
     】,
    0.45
    ဠ
    0.45
    ﺀ
    0.44
     বিটিআই
    0.44
    ㄽ
    0.43
     "????.??.??"]
    0.42
     মুক্তিফৌজ
    0.42
    POSITIVE LOGITS
        
    0.71
            
    0.63
       
    0.61
    i
    0.61
      
    0.58
         
    0.57
    #
    0.57
    o
    0.56
    er
    0.54
           
    0.54
    Act Density 0.291%

    No Known Activations