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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    indle
    -0.08
    心裡
    -0.07
    isnan
    -0.07
    .Small
    -0.07
     chimney
    -0.07
    ﻴ
    -0.07
    unger
    -0.06
    创新型
    -0.06
    CommandLine
    -0.06
    (isolate
    -0.06
    POSITIVE LOGITS
     Ahead
    0.07
     congestion
    0.07
    均为
    0.07
    ahr
    0.07
    如实
    0.07
     institution
    0.07
    .Please
    0.07
     influences
    0.07
    @section
    0.07
    渊
    0.07
    Act Density 0.083%

    No Known Activations