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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     fluids
    -0.07
     contributions
    -0.07
     Speakers
    -0.07
     Saints
    -0.07
    kills
    -0.07
     laboratories
    -0.07
     DependencyProperty
    -0.07
    Chair
    -0.07
     Isles
    -0.07
     rifle
    -0.06
    POSITIVE LOGITS
    𑂄
    0.07
    Serialized
    0.07
    ilty
    0.07
     recommand
    0.07
    ᗢ
    0.07
     raj
    0.07
     debacle
    0.06
    FIXME
    0.06
     perverse
    0.06
    مساب
    0.06
    Act Density 0.007%

    No Known Activations