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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     willpower
    1.02
    Pokud
    0.96
    Những
    0.93
     ľudí
    0.92
     aquilo
    0.90
    Waar
    0.89
     അല്ലെങ്കിൽ
    0.89
     തുടങ്ങിയ
    0.87
     eficiência
    0.86
     şeyler
    0.86
    POSITIVE LOGITS
    ↵↵
    0.79
     a
    0.78
    ↵
    0.77
    .
    0.76
    '.
    0.73
    vide
    0.73
    nders
    0.72
    𝓪
    0.71
     dengan
    0.71
    にて
    0.71
    Act Density 0.012%

    No Known Activations