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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    లు
    0.85
    contribution
    0.83
    لې
    0.81
    偖
    0.79
    useful
    0.78
    㕸
    0.76
    倆
    0.74
     Sections
    0.74
     mempunyai
    0.73
     আর্জেন্ট
    0.73
    POSITIVE LOGITS
     불구하고
    0.84
     كانت
    0.80
     regreso
    0.75
    érrez
    0.73
     Zuckerberg
    0.72
     마찬가지
    0.70
     antes
    0.68
     была
    0.68
     antigua
    0.68
     وكانت
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.