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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     parametrization
    0.86
     polymerization
    0.82
     अधीनस्थों
    0.81
     metamorphic
    0.80
     рады
    0.80
    こと
    0.79
     conversar
    0.79
     linewidth
    0.77
     紙
    0.77
     analyzed
    0.77
    POSITIVE LOGITS
    al
    0.85
    in
    0.82
    ación
    0.78
    ato
    0.77
    oric
    0.77
    u
    0.75
    er
    0.74
    "
    0.73
    max
    0.73
    💯
    0.73
    Act Density 0.000%

    No Known Activations