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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     IUnary
    0.60
     QnrB
    0.53
     cardNumber
    0.52
     তা
    0.50
     Affidavit
    0.50
     ReturnVal
    0.50
    🎱
    0.49
     Pacquiao
    0.49
     ServicePolicy
    0.48
     secretary
    0.48
    POSITIVE LOGITS
    cedes
    0.43
    akas
    0.42
    cache
    0.42
    immel
    0.41
    opf
    0.40
    msub
    0.39
    旪
    0.39
    eleng
    0.38
    concurrent
    0.38
    lando
    0.38
    Act Density 0.001%

    No Known Activations