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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     huh
    0.80
     porches
    0.76
     semicon
    0.75
     ойноо
    0.75
     valuations
    0.75
     downlink
    0.74
     bioinformatics
    0.73
     vững
    0.73
     Gradle
    0.73
     Banana
    0.73
    POSITIVE LOGITS
    ра
    0.97
    ка
    0.91
    朋友
    0.85
    ע
    0.80
    tedir
    0.80
    之前
    0.77
    ie
    0.75
    了一个
    0.74
    ى
    0.73
    木
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.