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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    우
    1.10
    ة
    0.99
    сида
    0.98
    $
    0.98
    वानगी
    0.96
     PNC
    0.93
    还有一个
    0.92
     Abgerufen
    0.91
    是一些
    0.91
     soluble
    0.89
    POSITIVE LOGITS
    em
    1.25
    ចិត្ត
    1.20
    at
    1.20
    ﹣
    1.20
    como
    1.18
    Brains
    1.17
     hér
    1.16
    諧
    1.15
    谐
    1.15
     khách
    1.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.