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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ל
    1.68
    ar
    1.52
    ע
    1.46
    an
    1.42
    ur
    1.42
    ن
    1.36
    l
    1.34
    ন
    1.33
    ר
    1.30
    на
    1.27
    POSITIVE LOGITS
    ς
    0.97
     \%$
    0.93
     tqdm
    0.86
     purpure
    0.86
     asyncio
    0.86
     acrylate
    0.84
    rcParams
    0.83
     значит
    0.82
     очередь
    0.82
     aceptar
    0.82
    Act Density 0.000%

    No Known Activations