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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ރ
    0.83
    AR
    0.80
    ف
    0.78
    жима
    0.77
    ید
    0.77
    ﺑ
    0.76
    IN
    0.75
    gence
    0.74
    idbody
    0.73
    ﻧ
    0.71
    POSITIVE LOGITS
     patties
    0.81
     ustedes
    0.75
     alliances
    0.73
     panes
    0.72
     ardu
    0.71
     apprentices
    0.71
    🤔
    0.71
     pars
    0.70
     چی
    0.69
     coils
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.