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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gear
    -0.70
     ib
    -0.65
    kernel
    -0.65
    collect
    -0.62
    steamapps
    -0.61
     Registration
    -0.60
    argon
    -0.60
    HOME
    -0.59
     Correspond
    -0.59
     perl
    -0.59
    POSITIVE LOGITS
    efully
    0.79
    azes
    0.77
    umbs
    0.75
    anqu
    0.74
    ayan
    0.72
    eful
    0.70
    ason
    0.70
    orthy
    0.69
    aby
    0.69
    oves
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.