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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    KindOfClass
    0.91
    を使
    0.83
     verko
    0.81
     reckoning
    0.80
     tinge
    0.80
    лению
    0.79
     mdl
    0.78
    ాలే
    0.78
     irradiance
    0.77
     absor
    0.77
    POSITIVE LOGITS
    j
    0.84
    \(
    0.80
    tar
    0.77
    ires
    0.77
    ма
    0.75
    {
    0.74
    ait
    0.74
    illa
    0.70
    \"{
    0.70
    በ
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.