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

    Neuronpedia

    INDEX
    Explanations

    developer ₹

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PAGE
    0.50
     page
    0.50
     Page
    0.47
    page
    0.45
    Page
    0.45
    Pag
    0.42
     página
    0.41
     xii
    0.39
    ListPage
    0.38
     PAGE
    0.38
    POSITIVE LOGITS
    ท่อง
    0.40
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
    つの
    0.38
    周年
    0.37
    fclose
    0.37
    礴
    0.37
     চাহিদা
    0.36
    년을
    0.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.34
     ஆண்டுகளாக
    0.34
    Act Density 0.003%

    No Known Activations