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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <unused2197>
    1.51
    <unused2199>
    1.42
    <unused2213>
    1.39
    <unused2231>
    1.30
    <unused2221>
    1.29
    <unused2165>
    1.26
    <unused2206>
    1.24
    <unused2137>
    1.22
    <unused2169>
    1.22
    1.21
    POSITIVE LOGITS
      
    2.05
     जिसमे
    2.01
     बच्चो
    1.99
     ايضا
    1.98
     नही
    1.94
     ,
    1.89
     tambien
    1.88
     میتوان
    1.88
     महिलाओ
    1.82
     কারন
    1.80
    Act Density 2.399%

    No Known Activations