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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    siz
    0.93
    s
    0.93
    ない
    0.91
    ों
    0.90
    sı
    0.88
    𝘀
    0.84
    lerini
    0.84
    lerin
    0.83
     sén
    0.82
    ς
    0.82
    POSITIVE LOGITS
    ਾ
    0.89
     perceptible
    0.84
     condesc
    0.84
     vehemently
    0.83
    on
    0.80
    et
    0.80
     dimensionless
    0.79
    于是
    0.79
    ষধ
    0.79
    EMENT
    0.78
    Act Density 0.000%

    No Known Activations