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

    Neuronpedia

    INDEX
    Explanations

    LaTeX document section ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Messieurs
    0.39
    മീ
    0.39
    চিব
    0.38
     बेटर
    0.38
    ूरत
    0.38
    ráf
    0.37
    願意
    0.37
    ছাড়া
    0.37
    yesi
    0.36
    <unused682>
    0.36
    POSITIVE LOGITS
    title
    0.44
    TITLE
    0.44
     Title
    0.43
     thro
    0.43
     title
    0.39
    Title
    0.39
     {\
    0.39
     preamble
    0.39
     \
    0.38
     TITLE
    0.38
    Act Density 0.001%

    No Known Activations