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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [prop
    -0.07
     discounts
    -0.07
    יז
    -0.07
    ϳ
    -0.06
    比利时
    -0.06
     baise
    -0.06
     payer
    -0.06
    פרויקט
    -0.06
    wide
    -0.06
    占据
    -0.06
    POSITIVE LOGITS
    莼
    0.08
    UIKit
    0.07
    _help
    0.07
    แก
    0.07
     stems
    0.07
     iam
    0.07
     designed
    0.06
    是怎么
    0.06
    .rawQuery
    0.06
     middleware
    0.06
    Act Density 0.276%

    No Known Activations