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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    乐观
    0.49
    nutí
    0.47
    分裂
    0.43
    焦虑
    0.42
    临床
    0.42
     Dự
    0.42
    漂
    0.41
    二百
    0.41
    платно
    0.40
    高效
    0.40
    POSITIVE LOGITS
     garis
    0.52
     simonsen
    0.48
     possui
    0.46
     trainer
    0.46
     ran
    0.46
     analyser
    0.46
     palm
    0.45
     fawn
    0.45
     تب
    0.44
     estavam
    0.44
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.