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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     agreements
    1.40
     axioms
    1.34
     fermions
    1.34
     models
    1.30
     boundaries
    1.28
    manship
    1.28
     angles
    1.27
     abilities
    1.27
     hues
    1.27
     frameworks
    1.27
    POSITIVE LOGITS
    😱
    1.20
     viêm
    1.17
     두
    1.15
    Coronavirus
    1.04
     causada
    1.03
    _{-}^{
    1.02
    ^{+}
    1.01
    😢
    1.01
    lantern
    1.00
     Д
    0.98
    Act Density 1.101%

    No Known Activations