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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    宾
    0.51
    enza
    0.45
    Calibration
    0.43
    賓
    0.42
    Rescue
    0.41
    DeviceCompliance
    0.41
     బ
    0.40
    jaman
    0.39
    循环
    0.39
    ิทธิ์
    0.39
    POSITIVE LOGITS
     entrants
    0.52
     Ordinary
    0.51
    !:
    0.50
     disponibles
    0.49
     ordinary
    0.48
     unchanged
    0.47
     sweats
    0.47
     unaffected
    0.46
     opposes
    0.46
     NPCs
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.