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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Pattern
    0.50
    Gra
    0.48
    Laboratory
    0.47
    Ley
    0.47
    Formula
    0.46
    Once
    0.46
    Brad
    0.46
     ley
    0.46
    R
    0.46
    James
    0.45
    POSITIVE LOGITS
    гів
    0.55
    ização
    0.50
     eficiência
    0.50
     engulfed
    0.49
    efficiencies
    0.47
     효율
    0.47
     nirvach
    0.46
     déplacements
    0.46
    یس
    0.45
     Pampl
    0.45
    Act Density 0.002%

    No Known Activations