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

    Neuronpedia

    INDEX
    Explanations

    Assert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    291
    -0.07
    loub
    -0.06
    mıştı
    -0.06
     prostituer
    -0.06
    ampiyon
    -0.06
    piler
    -0.06
    Subscriber
    -0.06
     unzip
    -0.06
     流
    -0.06
    。これ
    -0.06
    POSITIVE LOGITS
     Virginia
    0.07
     certainty
    0.07
     Zodiac
    0.07
     claws
    0.07
     evidently
    0.06
    ograph
    0.06
     producer
    0.06
     statute
    0.06
     Slovakia
    0.06
     modo
    0.06
    Act Density 0.005%

    No Known Activations