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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ल्लिंग
    1.34
     Tripathi
    1.30
    sag
    1.24
     Compression
    1.18
    speaker
    1.16
     Carth
    1.16
    sels
    1.16
     کننده
    1.14
    sending
    1.14
     Discharge
    1.13
    POSITIVE LOGITS
    м
    1.68
    ya
    1.63
    ak
    1.59
    ۰
    1.52
    б
    1.51
    لا
    1.48
    mio
    1.44
    మ
    1.43
    ંજ
    1.41
    ہ
    1.41
    Act Density 0.351%

    No Known Activations