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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ballroom
    0.73
     slowest
    0.71
     replaceable
    0.70
     underwhelming
    0.70
     tremendous
    0.69
     incredible
    0.69
     hilarious
    0.69
     railroads
    0.68
     bind
    0.68
     immobilized
    0.67
    POSITIVE LOGITS
    Among
    0.72
    २
    0.72
    六
    0.69
    成分
    0.68
    Nature
    0.68
    ١
    0.68
    Power
    0.66
    ٢
    0.66
    Six
    0.66
     다섯
    0.65
    Act Density 0.003%

    No Known Activations