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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Pokemon
    -0.95
    hare
    -0.74
     ILCS
    -0.72
     Yosemite
    -0.70
    FactoryReloaded
    -0.70
    hered
    -0.70
    poke
    -0.68
    onomic
    -0.67
    forge
    -0.66
    Downloadha
    -0.66
    POSITIVE LOGITS
    ģ«
    0.69
    oks
    0.63
     oath
    0.62
     Origin
    0.62
     policing
    0.61
     Rounds
    0.60
     gland
    0.60
     rampant
    0.59
     adjud
    0.59
     maneuver
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.