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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .leave
    -0.07
    /con
    -0.07
    _UN
    -0.07
    神
    -0.07
     confort
    -0.06
     alc
    -0.06
    .lin
    -0.06
     mon
    -0.06
     trains
    -0.06
    /people
    -0.06
    POSITIVE LOGITS
     Viet
    0.07
    -api
    0.06
     brilliantly
    0.06
    (itemView
    0.06
    {}".
    0.06
    itative
    0.06
     oversees
    0.06
    'order
    0.06
     نظری
    0.06
    ایی
    0.06
    Act Density 0.002%

    No Known Activations