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

    Neuronpedia

    INDEX
    Explanations

    idea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transmitted
    -0.08
    .production
    -0.07
     detecting
    -0.06
     recordings
    -0.06
     unfortunately
    -0.06
    names
    -0.06
     Sites
    -0.06
     ولم
    -0.06
     counts
    -0.06
    sources
    -0.06
    POSITIVE LOGITS
     idea
    0.11
     Idea
    0.07
    ۲۰۱
    0.07
    а
    0.07
     notion
    0.07
     hashed
    0.07
     Boca
    0.07
    Wr
    0.06
    Ide
    0.06
     Pagination
    0.06
    Act Density 0.019%

    No Known Activations