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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     comenzar
    1.00
    𝘦
    0.95
    𝖘
    0.90
     staffing
    0.88
     gratifying
    0.88
     စ
    0.86
     dalamnya
    0.86
     numerosas
    0.86
     berfungsi
    0.84
    𝘶
    0.83
    POSITIVE LOGITS
    a
    0.82
    د
    0.80
    ג
    0.79
     Rates
    0.78
    uction
    0.77
    و
    0.76
    ی
    0.75
    c
    0.71
    ل
    0.71
    i
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.