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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     incompet
    0.44
     слабо
    0.44
    ტორი
    0.40
    consider
    0.39
     Alonzo
    0.39
     profusely
    0.38
    orbit
    0.38
    hard
    0.38
     conspicuously
    0.38
     alcoved
    0.38
    POSITIVE LOGITS
     Yoga
    0.50
    ˊ
    0.49
     rumores
    0.49
     Params
    0.48
     quà
    0.48
    резать
    0.47
    ᒧ
    0.46
     dreamer
    0.45
     orgánica
    0.45
     mutta
    0.44
    Act Density 0.007%

    No Known Activations