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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     stable
    0.51
    穩
    0.50
     unstable
    0.48
     стаби
    0.47
     instability
    0.45
     Stable
    0.43
     안정
    0.42
     stabilize
    0.42
     steady
    0.42
     ổn
    0.42
    POSITIVE LOGITS
    noti
    0.56
     নোট
    0.52
     नोट
    0.46
    Notes
    0.46
     نوٹ
    0.44
     noter
    0.43
     Noether
    0.43
     notar
    0.43
    Notre
    0.42
    Pager
    0.42
    Act Density 0.026%

    No Known Activations