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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     reformed
    1.25
     strongly
    1.23
     rusak
    1.19
    ра
    1.19
     softened
    1.19
     resorption
    1.18
     vanished
    1.17
     softening
    1.16
     concealed
    1.15
    ا
    1.14
    POSITIVE LOGITS
    л
    1.27
    ので
    1.22
    ar
    1.10
    百科
    1.05
    한
    1.02
    er
    0.97
    ፈጥ
    0.95
    جلس
    0.91
    essayer
    0.91
    不了
    0.89
    Act Density 0.000%

    No Known Activations