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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     overseeing
    0.79
    roke
    0.73
     bern
    0.73
     Arteta
    0.72
    th
    0.72
    throwing
    0.71
     दिखाते
    0.71
     mewah
    0.71
    ੳ
    0.71
    founded
    0.70
    POSITIVE LOGITS
     deduce
    0.75
    고
    0.73
    PTION
    0.73
    ין
    0.71
    Haupt
    0.69
    chluss
    0.68
    ीकरण
    0.67
     Tris
    0.66
     chủ
    0.66
    ר
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.