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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    eners
    0.56
    llabus
    0.54
    iftoire
    0.54
    versible
    0.52
    ǜ
    0.52
    ij
    0.52
    igrams
    0.51
    zovaniyu
    0.50
    agers
    0.49
    ómago
    0.48
    POSITIVE LOGITS
     the
    0.64
    。
    0.62
            
    0.58
    .
    0.58
      
    0.57
     también
    0.57
       
    0.56
     também
    0.56
             
    0.55
    Also
    0.55
    Act Density 1.880%

    No Known Activations