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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     oreilles
    0.47
    🔰
    0.46
     earmarked
    0.45
     ચા
    0.45
     inférieurs
    0.44
     Attorneys
    0.43
     அதிகம்
    0.43
     efficaces
    0.43
     stessi
    0.42
     frowned
    0.42
    POSITIVE LOGITS
    什么样的
    0.42
     verify
    0.40
    她的
    0.40
     spring
    0.39
    weave
    0.39
     h
    0.39
     winter
    0.39
    他的
    0.39
     nascent
    0.39
     geh
    0.39
    Act Density 0.005%

    No Known Activations