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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    אפליקציה
    -0.07
    Section
    -0.07
    奥运会
    -0.06
     findAll
    -0.06
     rendering
    -0.06
     sider
    -0.06
     validate
    -0.06
     Render
    -0.06
     Reader
    -0.06
    Checking
    -0.06
    POSITIVE LOGITS
    lifetime
    0.08
     económico
    0.08
    FOUNDATION
    0.08
    厖
    0.07
     ihtiyacı
    0.07
    أشخاص
    0.07
    分かり
    0.07
     עבודת
    0.07
    בלעדי
    0.07
    ôme
    0.07
    Act Density 0.092%

    No Known Activations