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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ಿಂತ
    0.81
    enderung
    0.77
    到的
    0.77
     જેટ
    0.75
    dyž
    0.73
    हांत
    0.71
    য়েড
    0.70
    વાથી
    0.69
    ரிடம்
    0.69
    ीजन
    0.68
    POSITIVE LOGITS
     for
    6.38
     для
    5.83
    for
    5.56
     für
    5.17
     pentru
    5.04
     untuk
    5.01
     voor
    4.98
    для
    4.83
    สำหรับ
    4.74
     för
    4.67
    Act Density 5.164%

    No Known Activations