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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     لیتے
    0.49
    价
    0.48
    িবাস
    0.47
     التش
    0.46
     मकान
    0.44
     сатып
    0.43
     ′
    0.43
     недвижи
    0.42
    మవు
    0.42
     signifie
    0.41
    POSITIVE LOGITS
    TON
    0.52
    ک
    0.47
    '
    0.46
    ス
    0.45
    נ
    0.45
    ন
    0.45
    removed
    0.44
    described
    0.44
    き
    0.44
    újo
    0.43
    Act Density 0.000%

    No Known Activations