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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     an
    0.95
     foresight
    0.93
     för
    0.92
     integrity
    0.91
     enlargement
    0.91
     execute
    0.91
     solidity
    0.89
     ذاتی
    0.89
     stability
    0.88
     residency
    0.88
    POSITIVE LOGITS
    c
    1.16
    cích
    1.06
    纷纷
    1.02
    s
    1.00
     meisjes
    0.94
    Cameras
    0.94
    >.</
    0.90
    f
    0.90
     filmp
    0.89
    v
    0.89
    Act Density 0.817%

    No Known Activations