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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     entryway
    0.86
     vitality
    0.86
    ⁶
    0.83
     exchange
    0.82
    ibilities
    0.80
    illa
    0.79
    у
    0.79
     impedance
    0.79
     dumbbells
    0.77
    exchange
    0.73
    POSITIVE LOGITS
     紫
    0.77
     页
    0.75
     河
    0.75
     地域
    0.74
    wne
    0.72
     frères
    0.71
    وأ
    0.71
    và
    0.70
     localhost
    0.70
    EAST
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.