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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    byn
    -0.70
    chy
    -0.69
    ZA
    -0.65
     Neighbor
    -0.62
    usted
    -0.61
    OT
    -0.61
    OTS
    -0.60
    ombo
    -0.59
    AW
    -0.59
     guilty
    -0.59
    POSITIVE LOGITS
     balance
    1.20
     Balance
    0.98
    Balance
    0.96
    balance
    0.91
    76561
    0.86
    addons
    0.76
    limits
    0.74
    imity
    0.70
    ylum
    0.67
     ILCS
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.