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

    Neuronpedia

    INDEX
    Explanations

    Spreadsheet fill handle dragging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Me
    -0.08
    ining
    -0.08
    /report
    -0.08
    éder
    -0.08
    -Me
    -0.07
    地下
    -0.07
    pi
    -0.07
    .separator
    -0.07
     Separ
    -0.07
     séparation
    -0.07
    POSITIVE LOGITS
     بزر
    0.08
     embedding
    0.08
     who's
    0.08
     faisant
    0.08
     populate
    0.08
     छ
    0.08
    做好
    0.07
     suuri
    0.07
    phans
    0.07
     করছি
    0.07
    Act Density 0.001%

    No Known Activations