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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     by
    0.45
     क
    0.43
    de
    0.43
     OD
    0.42
     rolled
    0.42
     overlap
    0.40
     admiral
    0.40
     y
    0.40
    在使用
    0.39
     de
    0.39
    POSITIVE LOGITS
    стаў
    0.45
    everything
    0.42
    μέν
    0.41
    юн
    0.40
    Ђ
    0.40
    ћ
    0.40
    kinase
    0.40
    ρέ
    0.39
    фона
    0.39
    леду
    0.39
    Act Density 0.000%

    No Known Activations