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

    Neuronpedia

    INDEX
    Explanations

    used to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Outputs
    -0.07
     পূর্ব
    -0.07
    输出
    -0.07
     Saunders
    -0.07
     vorz
    -0.07
     Output
    -0.07
     gelief
    -0.07
     fero
    -0.07
     ವಿಚ
    -0.07
     città
    -0.07
    POSITIVE LOGITS
    用于
    0.10
     continuation
    0.08
    .endpoint
    0.08
     initiatives
    0.08
    (endpoint
    0.08
     商品
    0.08
     купить
    0.08
     足
    0.08
    Continuation
    0.08
     买
    0.08
    Act Density 0.051%

    No Known Activations