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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    y
    0.98
    t
    0.92
    take
    0.84
    carry
    0.84
    table
    0.82
    sheet
    0.80
    á
    0.80
    tap
    0.80
    tion
    0.78
    m
    0.76
    POSITIVE LOGITS
     esforços
    0.88
     russo
    0.81
     populaire
    0.76
    الة
    0.75
     Futebol
    0.75
     ataques
    0.74
     alcoved
    0.73
    Ė
    0.72
     Commencez
    0.71
     parabol
    0.71
    Act Density 0.001%

    No Known Activations