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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    illac
    -0.94
    vernment
    -0.92
    agall
    -0.78
    uj
    -0.77
    rament
    -0.76
    nce
    -0.75
     spons
    -0.73
    rica
    -0.73
    orship
    -0.72
    ctor
    -0.72
    POSITIVE LOGITS
     Strikes
    0.73
    stones
    0.68
     Planes
    0.67
    Container
    0.66
     Cooldown
    0.66
     Delivery
    0.64
    ãĥĦ
    0.64
     RELEASE
    0.64
     Eyes
    0.64
    blade
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.