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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ragon
    -0.72
    asio
    -0.69
    actly
    -0.68
     spores
    -0.67
     pickups
    -0.67
     flashback
    -0.66
    anship
    -0.66
    gdala
    -0.66
     Bris
    -0.64
    anced
    -0.64
    POSITIVE LOGITS
    VB
    0.80
    swick
    0.75
    Ru
    0.71
    VD
    0.70
     Ware
    0.70
    utenberg
    0.67
    Medic
    0.66
    leck
    0.64
     Murdoch
    0.64
     Remain
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.