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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    0.89
     മാര്‍
    0.86
    ség
    0.83
    १
    0.82
     объем
    0.81
     ocasión
    0.78
    park
    0.77
    ab
    0.77
    фы
    0.76
    on
    0.75
    POSITIVE LOGITS
    裔
    0.81
     permettre
    0.80
     lesbians
    0.80
     prendre
    0.77
     grosseur
    0.77
     बाहेर
    0.77
     buts
    0.76
     besoins
    0.73
     quels
    0.73
     permettant
    0.72
    Act Density 0.000%

    No Known Activations