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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     interessa
    0.48
     перечис
    0.48
    人间
    0.47
    ेट
    0.44
    स्परिक
    0.44
     失
    0.44
    扆
    0.44
    బ్
    0.43
    ങ്ക്
    0.43
    apayati
    0.43
    POSITIVE LOGITS
              
    0.50
          
    0.50
             
    0.49
     menus
    0.47
    4
    0.47
     but
    0.46
    3
    0.46
     Politicians
    0.46
    こともある
    0.46
                
    0.45
    Act Density 0.002%

    No Known Activations