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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ilea
    0.41
    лено
    0.40
    Acceler
    0.40
    Combined
    0.38
     approximating
    0.38
     enormously
    0.38
    지컬
    0.38
     fabulous
    0.37
    තුර
    0.37
     bribery
    0.35
    POSITIVE LOGITS
    Autocomplete
    0.47
     Biochim
    0.41
     χω
    0.40
     Grim
    0.39
     međ
    0.39
     אני
    0.38
     участи
    0.37
     ined
    0.37
    rimidin
    0.37
     думаю
    0.37
    Act Density 0.000%

    No Known Activations