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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     icons
    0.55
     eligibility
    0.52
     accesses
    0.50
     measurements
    0.50
     idols
    0.48
     utilises
    0.48
     exploits
    0.48
     dependencies
    0.47
     plugs
    0.47
     subscriptions
    0.46
    POSITIVE LOGITS
    änz
    0.48
    睄
    0.48
    voř
    0.46
     previewBuilder
    0.45
     неожидан
    0.44
     MANUFACT
    0.44
     jīn
    0.44
     மாண
    0.44
    大きな
    0.44
    תר
    0.44
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.