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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，因为
    -0.07
     livest
    -0.07
     neuron
    -0.07
     niž
    -0.06
     ebook
    -0.06
     parasites
    -0.06
     Chem
    -0.06
     Samurai
    -0.06
    �
    -0.06
     supplier
    -0.06
    POSITIVE LOGITS
    edik
    0.07
    预览
    0.07
    chein
    0.07
    握
    0.06
    tweet
    0.06
    ichi
    0.06
     definit
    0.06
     goose
    0.06
     Tweet
    0.06
    ==============↵
    0.06
    Act Density 0.012%

    No Known Activations