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

    Neuronpedia

    INDEX
    Explanations

    configuration file paths, commands, and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ิบ
    0.44
     стоит
    0.42
     gypsy
    0.41
     gynec
    0.39
     тура
    0.39
     中古
    0.39
     COO
    0.39
    ถือ
    0.39
    ่ย
    0.38
    ONTAL
    0.38
    POSITIVE LOGITS
          
    0.73
         
    0.62
        
    0.61
              
    0.59
            
    0.59
                
    0.58
           
    0.56
               
    0.53
       
    0.51
    0.48
    Act Density 0.005%

    No Known Activations