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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    з
    1.14
     основы
    0.93
    ro
    0.88
    о
    0.86
    お店
    0.86
     এজন্য
    0.82
     бою
    0.79
    ু
    0.79
     manifest
    0.79
    в
    0.79
    POSITIVE LOGITS
    های
    1.19
     tég
    1.04
    เอียด
    1.00
    ettings
    1.00
    Unable
    0.99
     lm
    0.97
    žiť
    0.96
    thats
    0.96
    ද්ධ
    0.93
    ektedir
    0.93
    Act Density 0.119%

    No Known Activations