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

    Neuronpedia

    INDEX
    Explanations

    filenames and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.96
    ...
    0.94
    \...
    0.90
    …
    0.80
    .+
    0.79
    \\
    0.78
    .\\
    0.76
    .}
    0.76
    .,
    0.75
    "
    0.75
    POSITIVE LOGITS
    ᐟ
    1.32
    jpg
    1.10
     godine
    0.99
     aasta
    0.96
    ＰＥＮＡＮＡ
    0.96
    png
    0.95
     pylori
    0.89
     coli
    0.88
     Архів
    0.87
     pneumoniae
    0.87
    Act Density 0.729%

    No Known Activations