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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ak
    1.05
    ik
    1.00
    ag
    0.95
    e
    0.92
    ig
    0.92
    à
    0.90
    ed
    0.89
    f
    0.87
    ess
    0.84
    elt
    0.82
    POSITIVE LOGITS
     legislators
    0.90
    이죠
    0.90
    criminals
    0.89
    Ճ
    0.88
     grayscale
    0.88
    นี้
    0.86
     sidan
    0.86
     complainants
    0.85
     ವಿರು
    0.85
     तैनात
    0.84
    Act Density 0.000%

    No Known Activations