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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cabbage
    0.47
    ធី
    0.44
     seabed
    0.44
     property
    0.43
    )}$
    0.43
     నీ
    0.43
     अवस्थ
    0.43
    $&$-
    0.42
    \}_{
    0.42
    Yvette
    0.42
    POSITIVE LOGITS
    っています
    0.52
    fst
    0.49
     artificially
    0.49
    ری
    0.48
     İran
    0.48
    Мы
    0.47
    স্ট্র
    0.47
    ક્ટ
    0.46
    Ἱ
    0.46
    훈련
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.