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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Polymers
    0.85
     Boosting
    0.80
     Erosion
    0.79
     Lending
    0.77
     활용
    0.77
    ພວກເຮົາ
    0.77
     انج
    0.76
     upsets
    0.75
     Leveraging
    0.75
     خوا
    0.75
    POSITIVE LOGITS
    per
    0.82
    u
    0.75
    busy
    0.75
    ø
    0.74
    comp
    0.70
    quiet
    0.69
    er
    0.68
    лось
    0.68
     když
    0.67
    company
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.