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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lemagne
    0.89
     shea
    0.80
    karte
    0.80
     foothills
    0.79
    ̌
    0.78
     irreparable
    0.78
     Neh
    0.77
     Peru
    0.77
    ängt
    0.77
     cilantro
    0.76
    POSITIVE LOGITS
    станови
    0.80
    아
    0.77
    는
    0.76
     свър
    0.76
    리에
    0.75
    съ
    0.75
     그러면
    0.75
    على
    0.74
    Factory
    0.73
    现在
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.