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

    Neuronpedia

    INDEX
    Explanations

    roads/routes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拓
    -0.07
     backpack
    -0.07
     Backpack
    -0.07
     durumunda
    -0.06
    olesale
    -0.06
    .author
    -0.06
    某
    -0.06
    	MessageBox
    -0.06
    ễ
    -0.06
    (extension
    -0.06
    POSITIVE LOGITS
     je
    0.07
     Winter
    0.06
     ihrer
    0.06
     Ik
    0.06
     inevitably
    0.06
    će
    0.06
    زو
    0.06
    lero
    0.06
     ho
    0.06
    自動
    0.06
    Act Density 0.202%

    No Known Activations