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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     battlefield
    0.41
     может
    0.40
     வா
    0.40
     batalla
    0.39
    रानी
    0.38
    ujete
    0.38
     вече
    0.38
    링
    0.37
     и
    0.37
    ν
    0.37
    POSITIVE LOGITS
     Astoria
    0.40
     Astrid
    0.39
     Honour
    0.39
     swatch
    0.39
    秝
    0.39
     Anci
    0.38
    apod
    0.38
     للنساء
    0.38
    brevi
    0.38
    Multicolored
    0.37
    Act Density 0.000%

    No Known Activations