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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \&
    0.71
    Thor
    0.69
    Berry
    0.69
    NSArray
    0.67
    Bes
    0.66
    जानिए
    0.64
     threatening
    0.64
    chyma
    0.64
     threatened
    0.64
     ജില്ല
    0.63
    POSITIVE LOGITS
     //
    1.51
     #
    1.25
      
    1.16
       
    1.15
             
    1.07
           
    1.06
                 
    1.03
         
    1.02
                     
    1.02
               
    1.01
    Act Density 1.396%

    No Known Activations