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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cops
    0.74
     unions
    0.68
     Unis
    0.66
     Union
    0.66
    ASHINGTON
    0.66
    </table>
    0.64
     Fisherman
    0.64
    ल
    0.63
    დეს
    0.63
     tableau
    0.63
    POSITIVE LOGITS
     fikk
    0.91
     kuulu
    0.91
     ebbe
    0.88
     وعلى
    0.83
    что
    0.82
     habt
    0.81
     mevcut
    0.81
     edifício
    0.80
     что
    0.80
     этот
    0.80
    Act Density 0.000%

    No Known Activations