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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sgd
    1.24
    КО
    1.24
    dup
    1.23
    係る
    1.23
    ﻘ
    1.23
     opět
    1.23
     лицом
    1.22
    ਼
    1.21
     vých
    1.20
     깔
    1.19
    POSITIVE LOGITS
    ‍♀️
    0.92
    ות
    0.92
    else
    0.91
    தர்
    0.89
    }}\,
    0.87
     Το
    0.86
    chten
    0.85
    chmal
    0.85
    thers
    0.85
    ewhere
    0.85
    Act Density 0.000%

    No Known Activations