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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    devamını
    -0.39
     apon
    -0.38
     Kessel
    -0.36
    pregnant
    -0.36
     Janssen
    -0.35
    empêcher
    -0.35
     gerichtet
    -0.35
    FontOfSize
    -0.35
      (
    -0.35
     constituting
    -0.33
    POSITIVE LOGITS
    :✨
    0.84
    Personensuche
    0.69
    RegressionTest
    0.62
     ***!
    0.53
     мәкал
    0.53
     unknownFields
    0.52
    verifyException
    0.52
    Personendaten
    0.51
     Numerade
    0.50
     referenties
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.