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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     projections
    0.69
     gilt
    0.65
     animations
    0.65
     .
    0.64
    period
    0.63
     manuscripts
    0.60
     vast
    0.59
     teachings
    0.59
    projects
    0.59
    trace
    0.59
    POSITIVE LOGITS
    Waar
    0.96
    ل
    0.95
    ম
    0.88
     дві
    0.85
    Während
    0.85
     簡単
    0.84
     最初
    0.84
     ம
    0.83
    imcoords
    0.83
    ﻘ
    0.82
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.