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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     hoard
    0.39
     pourtant
    0.39
    ត្
    0.38
     reliance
    0.38
     complexities
    0.38
    certificates
    0.38
     comparisons
    0.37
     mathematicians
    0.37
    ભ
    0.37
     breakthrough
    0.37
    POSITIVE LOGITS
    栻
    0.42
    滖
    0.41
    ,...,
    0.39
     സൂര്യ
    0.39
    綃
    0.38
    लेरिया
    0.37
     !!,
    0.37
     。,
    0.37
     culturel
    0.36
    étend
    0.36
    Act Density 0.000%

    No Known Activations