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

    Neuronpedia

    INDEX
    Explanations

    news article background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Idx
    -0.08
     😉↵↵
    -0.08
     常
    -0.08
     intuition
    -0.08
    	idx
    -0.08
     기본
    -0.08
    _idxs
    -0.08
    intu
    -0.07
     😉
    -0.07
     مناسب
    -0.07
    POSITIVE LOGITS
    据了解
    0.12
    警方
    0.10
    新闻
    0.10
    ，公司
    0.10
     journalists
    0.10
     rumores
    0.10
     Reuters
    0.10
     spokesperson
    0.10
    Reuters
    0.10
    报道
    0.10
    Act Density 0.028%

    No Known Activations