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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Religion
    0.50
    American
    0.47
    Key
    0.47
    Language
    0.45
    Old
    0.45
    Options
    0.45
    Animal
    0.45
    key
    0.44
    Sum
    0.44
    Code
    0.44
    POSITIVE LOGITS
    ®.
    0.63
    ®
    0.61
     adlı
    0.61
     spp
    0.60
     GmbH
    0.56
     itself
    0.54
     नामक
    0.53
     sendiri
    0.53
     Ltd
    0.52
    及其
    0.52
    Act Density 0.787%

    No Known Activations