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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     récord
    0.52
    zoomSeekBar
    0.52
     Оюн
    0.49
    ногие
    0.49
     radiate
    0.49
     Higgs
    0.48
    踰
    0.48
    <unused2231>
    0.48
    境界層
    0.47
     |.
    0.47
    POSITIVE LOGITS
    akt
    0.51
    HAR
    0.50
    ast
    0.48
    平
    0.47
    Adapter
    0.46
    ente
    0.46
    imi
    0.44
    里
    0.44
    ize
    0.44
    CM
    0.44
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.