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

    Neuronpedia

    INDEX
    Explanations

    people and entities

    np_acts-logits-general · gemini-2.5-flash-lite

    of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
              
    0.20
         
    0.19
             
    0.18
    ↵
    0.18
        
    0.18
    </b>
    0.17
                                   
    0.17
           
    0.16
               
    0.16
                         
    0.16
    POSITIVE LOGITS
     another
    0.25
     ANOTHER
    0.22
     hubby
    0.21
     some
    0.20
     someone
    0.20
     everyone
    0.20
     Coldplay
    0.20
     LeBron
    0.19
     Rihanna
    0.19
     whoever
    0.19
    Act Density 8.676%

    No Known Activations