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

    Neuronpedia

    INDEX
    Explanations

    Code/technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mineral
    -0.07
    DEM
    -0.06
     características
    -0.06
     aides
    -0.06
     specs
    -0.06
    carrier
    -0.06
     square
    -0.06
    ure
    -0.06
    PA
    -0.06
    URE
    -0.06
    POSITIVE LOGITS
    出す
    0.07
     Mostly
    0.07
     PS
    0.06
     Pension
    0.06
     serialVersionUID
    0.06
    дяки
    0.06
    .Closed
    0.06
     هنا
    0.06
     casualties
    0.06
    สอง
    0.06
    Act Density 0.131%

    No Known Activations