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

    Neuronpedia

    INDEX
    Explanations

    attention-grabbing content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ो,
    -0.06
    排
    -0.06
     icy
    -0.06
     reception
    -0.06
    _costs
    -0.06
    .payload
    -0.05
    difficulty
    -0.05
     cancellation
    -0.05
     recommand
    -0.05
    -com
    -0.05
    POSITIVE LOGITS
     شي
    0.07
     olup
    0.07
     sealed
    0.07
     cherish
    0.06
     spiders
    0.06
    قيق
    0.06
    _ALWAYS
    0.06
     такой
    0.06
     Lanka
    0.06
     (...)
    0.06
    Act Density 0.024%

    No Known Activations