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

    Neuronpedia

    INDEX
    Explanations

    about and like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अथवा
    0.20
     valamint
    0.19
        
    0.18
       
    0.18
    ※
    0.18
         
    0.18
    ,-
    0.18
    <unused2121>
    0.18
          
    0.17
           
    0.17
    POSITIVE LOGITS
     về
    0.38
     like
    0.37
     about
    0.37
     akin
    0.37
     tentang
    0.36
     meant
    0.35
    เหมือน
    0.33
     what
    0.31
     عن
    0.31
     ABOUT
    0.31
    Act Density 0.241%

    No Known Activations