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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     inclined
    1.28
     Freiheit
    1.15
     tying
    1.15
     srps
    1.10
     svih
    1.07
     defy
    1.05
     willst
    1.04
     १०
    1.04
     simak
    1.04
     functors
    1.03
    POSITIVE LOGITS
    갖
    1.28
    giver
    1.24
     référence
    1.20
     stagnation
    1.17
    কালের
    1.16
    bagian
    1.14
    ஆம்
    1.14
     मुंह
    1.11
    ्राष्ट्रीय
    1.10
    ∆
    1.10
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.