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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dece
    -0.07
     Breast
    -0.07
     Vista
    -0.06
    705
    -0.06
     workout
    -0.06
    Bir
    -0.06
     paints
    -0.06
     Sorting
    -0.06
     Ör
    -0.06
     Dias
    -0.06
    POSITIVE LOGITS
    人員
    0.08
    ٫
    0.08
     <*>
    0.07
    はい
    0.07
    Seeder
    0.06
    (FALSE
    0.06
    ultureInfo
    0.06
    .Read
    0.06
    -answer
    0.06
    хови
    0.06
    Act Density 0.014%

    No Known Activations