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

    Neuronpedia

    INDEX
    Explanations

    file extensions pdf and jpg

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scripts
    0.48
    cripts
    0.39
    Config
    0.38
    Python
    0.38
    脚本
    0.38
     configs
    0.38
    ণির
    0.37
    Configs
    0.36
     playlists
    0.36
     script
    0.36
    POSITIVE LOGITS
    pdf
    0.71
     pdf
    0.65
     Pdf
    0.57
     PDF
    0.50
    PDF
    0.47
    jpg
    0.45
    zip
    0.45
    gif
    0.43
    Pdf
    0.42
    png
    0.41
    Act Density 0.004%

    No Known Activations