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

    Neuronpedia

    INDEX
    Explanations

    protected

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    traction
    -0.07
    ActivityIndicatorView
    -0.07
     manifest
    -0.07
    白癜
    -0.07
     swing
    -0.07
     يعني
    -0.07
    .newInstance
    -0.07
    .Is
    -0.06
    终极
    -0.06
    兒童
    -0.06
    POSITIVE LOGITS
    href
    0.08
     genders
    0.07
    走廊
    0.07
     цены
    0.07
    튽
    0.07
    nofollow
    0.07
     Markdown
    0.07
    没办法
    0.07
     composers
    0.07
     tamaño
    0.07
    Act Density 0.003%

    No Known Activations