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

    Neuronpedia

    INDEX
    Explanations

    transposing or transforming elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    重要
    1.64
    ب
    1.48
    لان
    1.31
    新兴
    1.18
    ج
    1.16
    embangunan
    1.16
     важных
    1.15
    ه
    1.14
     самое
    1.13
     необходимых
    1.10
    POSITIVE LOGITS
    nal
    1.23
    taining
    1.19
    alho
    1.17
     presa
    1.17
    tive
    1.11
    ueel
    1.10
    deload
    1.09
    ፩
    1.09
    wreck
    1.09
    tle
    1.06
    Act Density 0.000%

    No Known Activations