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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     zwar
    1.17
    lor
    1.14
     gl
    1.14
     namely
    1.08
     dand
    1.06
     પાસેથી
    0.98
     తో
    0.97
     damit
    0.96
    Serialized
    0.96
    Miles
    0.95
    POSITIVE LOGITS
    骓
    1.25
    定律
    1.24
    krét
    1.22
    щик
    1.21
     drags
    1.20
     ambulatory
    1.20
    絶対
    1.20
     mydict
    1.18
    étaient
    1.17
    т
    1.17
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.