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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arrivals
    0.92
    argaan
    0.89
     //#
    0.87
    fulness
    0.86
    ful
    0.86
    orado
    0.84
    usk
    0.84
    engo
    0.82
     belle
    0.81
    ¾
    0.81
    POSITIVE LOGITS
     적용
    1.00
    Path
    0.95
     combinación
    0.90
    рати
    0.90
     demás
    0.89
     média
    0.88
    जन्य
    0.87
    ніза
    0.86
    Subjects
    0.86
     아닌
    0.85
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.