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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     salah
    0.77
     Такие
    0.74
    etano
    0.74
     ফ্লাইট
    0.73
    比較的
    0.72
    品種
    0.68
    積極
    0.66
     ilyen
    0.66
    Innovative
    0.66
    стного
    0.66
    POSITIVE LOGITS
     seluruh
    2.57
     entire
    2.52
     everything
    2.48
     world
    2.45
    整个
    2.32
     всему
    2.25
    everything
    2.24
     świata
    2.23
     EVERYTHING
    2.20
     kogu
    2.19
    Act Density 1.609%

    No Known Activations