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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    د
    1.37
     sats
    1.32
    𝐄
    1.31
     phir
    1.26
    流动
    1.25
     radiance
    1.25
    ﻖ
    1.23
    ﻰ
    1.22
     Roshan
    1.21
     aversion
    1.19
    POSITIVE LOGITS
     Seorang
    1.25
    ్
    1.11
    ా
    1.10
     सुनवाई
    1.03
    ы
    1.01
     Maret
    1.01
    โรค
    1.01
     zwar
    0.98
     एमएस
    0.96
     zwei
    0.96
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.