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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    2
    0.95
    4
    0.93
    5
    0.88
    3
    0.87
    1
    0.80
    7
    0.76
    0
    0.72
    6
    0.71
    8
    0.70
    iving
    0.66
    POSITIVE LOGITS
    dessus
    0.75
     Mentre
    0.71
    çok
    0.68
     skut
    0.67
     honti
    0.67
    кугӀ
    0.66
     በጣም
    0.66
     sesuai
    0.65
     ravine
    0.65
     மூலம்
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.