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

    Neuronpedia

    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     מכ
    -0.08
    是要
    -0.07
    .nc
    -0.06
     إلى
    -0.06
    天下
    -0.06
     Lore
    -0.06
    /music
    -0.06
    一万
    -0.06
     Mitt
    -0.06
    /_
    -0.06
    POSITIVE LOGITS
    DOWNLOAD
    0.07
     principalColumn
    0.07
     preserving
    0.06
     ואח
    0.06
     określon
    0.06
     researching
    0.06
    Deal
    0.06
    coach
    0.06
    eight
    0.06
     chatting
    0.06
    Act Density 0.008%

    No Known Activations