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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    >>,
    0.51
     isolates
    0.50
    ডেল
    0.50
     Varan
    0.50
     sabot
    0.49
     crise
    0.49
    ➟
    0.48
    сор
    0.48
    LLCATS
    0.48
    墂
    0.47
    POSITIVE LOGITS
    厭
    0.48
    ind
    0.46
    cond
    0.43
    ம
    0.42
    ин
    0.41
    מס
    0.41
    ica
    0.40
    城市
    0.40
    ilä
    0.40
    يث
    0.39
    Act Density 0.000%

    No Known Activations