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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     જેટ
    0.73
    到的
    0.71
    ीजन
    0.68
    हांत
    0.68
    ಲಿಲ್ಲ
    0.67
    मेज
    0.64
    ரிடம்
    0.63
    dyž
    0.63
    bildung
    0.63
    ობას
    0.62
    POSITIVE LOGITS
     for
    5.82
     для
    5.82
     für
    5.15
    for
    5.03
     pentru
    4.97
     voor
    4.93
     untuk
    4.90
    для
    4.86
    สำหรับ
    4.86
     dla
    4.68
    Act Density 4.235%

    No Known Activations