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

    Neuronpedia

    INDEX
    Explanations

    original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NS
    -0.08
    /maps
    -0.07
    甚
    -0.07
     Info
    -0.07
    アクセス
    -0.07
     discourage
    -0.07
     değerlendirme
    -0.06
    /authentication
    -0.06
    reating
    -0.06
     Review
    -0.06
    POSITIVE LOGITS
    тяж
    0.08
    手腕
    0.07
    的商品
    0.07
    ünkü
    0.07
     fueron
    0.06
    airy
    0.06
    -counter
    0.06
    Chunks
    0.06
     Bicycle
    0.06
    }'↵
    0.06
    Act Density 0.019%

    No Known Activations