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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     belangrijke
    0.64
     bilgil
    0.61
    重要的
    0.61
    ⓛ
    0.60
     memahami
    0.60
    ·
    0.60
    ⦁
    0.57
     mahasiswa
    0.56
    PointXYZ
    0.54
     devlet
    0.53
    POSITIVE LOGITS
     seems
    0.71
     https
    0.66
     Seems
    0.63
     Improvements
    0.59
     ("
    0.58
     Unfortunately
    0.58
    (
    0.57
    https
    0.56
     Both
    0.56
     apparently
    0.55
    Act Density 0.002%

    No Known Activations