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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     결혼
    -0.08
         ↵↵
    -0.07
     because
    -0.07
    亿
    -0.07
     BH
    -0.06
    'util
    -0.06
    redirect
    -0.06
     When
    -0.06
    ул
    -0.06
    ₁
    -0.06
    POSITIVE LOGITS
    eleri
    0.07
    oại
    0.06
     hätte
    0.06
    IRST
    0.06
    Parts
    0.05
    SD
    0.05
     stup
    0.05
    HandlerContext
    0.05
    ields
    0.05
    =msg
    0.05
    Act Density 0.195%

    No Known Activations