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

    Neuronpedia

    INDEX
    Explanations

    feature comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Diput
    0.38
     local
    0.37
     para
    0.37
     सभी
    0.36
     de
    0.36
     todos
    0.35
    ```{
    0.35
     atas
    0.35
     chicos
    0.34
     tabular
    0.34
    POSITIVE LOGITS
     коммента
    0.41
    commentaire
    0.41
    ერის
    0.39
     Significance
    0.37
    Comment
    0.37
    Explanation
    0.36
     liya
    0.36
     মনোভাব
    0.36
    een
    0.35
     penjelasan
    0.35
    Act Density 0.004%

    No Known Activations