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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    dar
    0.42
     lage
    0.41
     ale
    0.40
     okol
    0.39
     kev
    0.37
    侣
    0.37
    وظ
    0.36
    fall
    0.36
     leden
    0.36
    oda
    0.36
    POSITIVE LOGITS
     സ്വ
    0.48
     ಶ
    0.44
     अर्जेंटीना
    0.43
    牖
    0.43
     ዓይነ
    0.42
    Argentina
    0.41
     getImage
    0.40
     obtaining
    0.40
     Argentina
    0.39
     attaining
    0.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.