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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     środ
    -0.07
    .↵↵↵↵↵
    -0.07
     buc
    -0.07
     Page
    -0.07
     Panc
    -0.07
    entious
    -0.07
    reasonable
    -0.06
    仅供
    -0.06
    だし
    -0.06
    لان
    -0.06
    POSITIVE LOGITS
    を
    0.08
     они
    0.07
     ALWAYS
    0.07
    距離
    0.07
    輪
    0.07
    ring
    0.07
     hemisphere
    0.07
    網
    0.07
     squares
    0.07
    крат
    0.07
    Act Density 0.007%

    No Known Activations