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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.50
    s
    0.46
     almost
    0.45
      
    0.45
    t
    0.45
     sanity
    0.44
     compliance
    0.43
    y
    0.43
     minimal
    0.42
     invariant
    0.42
    POSITIVE LOGITS
     Пар
    0.56
     personaggio
    0.55
    ologija
    0.55
    ामान्य
    0.55
     menonton
    0.55
     personagens
    0.53
     personagem
    0.53
     その他
    0.53
     osobe
    0.53
    鶚
    0.53
    Act Density 0.005%

    No Known Activations