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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lie
    0.43
    讓我們
    0.42
    rino
    0.40
    lie
    0.39
    Lie
    0.39
    ೊಳ್ಳ
    0.39
    boe
    0.39
     পেঁয়
    0.38
    Lor
    0.37
    дзе
    0.37
    POSITIVE LOGITS
     contr
    0.41
     Douglas
    0.40
     intégré
    0.39
    द्वी
    0.37
     servi
    0.37
    Douglas
    0.37
     контра
    0.37
    விட்ட
    0.36
    GetAll
    0.36
    ādi
    0.36
    Act Density 0.000%

    No Known Activations