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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    1.20
     другое
    1.02
     пер
    0.95
    錘
    0.93
     др
    0.89
     همد
    0.89
     не
    0.88
     иде
    0.87
     শী
    0.87
     not
    0.86
    POSITIVE LOGITS
    Wes
    1.45
    MovieDetails
    1.44
    <unused2086>
    1.43
    Malcolm
    1.41
     দেওয়া
    1.40
     wisata
    1.36
    <unused1463>
    1.35
     powerhouse
    1.34
     shoreline
    1.34
     carreira
    1.34
    Act Density 0.000%

    No Known Activations