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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    fläche
    0.37
    冲
    0.37
     Flowers
    0.35
     NX
    0.35
     (!)
    0.34
    屈
    0.34
    NUMX
    0.34
    uciones
    0.34
     =======
    0.34
    incs
    0.33
    POSITIVE LOGITS
     एग्जाम्स
    0.41
     यूज
    0.39
     ಬಳಕೆ
    0.37
    뜹
    0.37
     मोस्ट
    0.37
     mario
    0.37
     використання
    0.36
    ONT
    0.35
    𝐘
    0.35
    𝒸
    0.35
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.