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

    Neuronpedia

    INDEX
    Explanations

    lower

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Balls
    -0.06
     snapped
    -0.06
    スタ
    -0.06
     blindly
    -0.06
     có
    -0.06
    Catalog
    -0.06
    itches
    -0.06
     bouncing
    -0.06
     وارد
    -0.06
     América
    -0.06
    POSITIVE LOGITS
    _pod
    0.07
    lower
    0.07
     Scalia
    0.07
     leaderboard
    0.06
    Inset
    0.06
    cased
    0.06
    imid
    0.06
     avantaj
    0.06
    사이
    0.06
    ตร
    0.06
    Act Density 0.002%

    No Known Activations