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

    Neuronpedia

    INDEX
    Explanations

    code compilation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    なのです
    -0.07
    蠃
    -0.07
    を使
    -0.07
    instanc
    -0.06
    	↵	↵	↵	↵
    -0.06
    "]))
    -0.06
     JText
    -0.06
    赢
    -0.06
    🇻
    -0.06
    越し
    -0.06
    POSITIVE LOGITS
    ,
    0.14
    ation
    0.10
     rotation
    0.08
     mariage
    0.08
    ção
    0.08
    版本
    0.08
    อาหาร
    0.08
    Build
    0.08
     shipment
    0.08
     integration
    0.08
    Act Density 1.713%

    No Known Activations