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

    Neuronpedia

    INDEX
    Explanations

    study analyze

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ايير
    -0.08
     تې
    -0.08
     ۋاقتى
    -0.08
     commemor
    -0.08
     قوم
    -0.08
    .bold
    -0.08
     ставка
    -0.08
     coveted
    -0.08
     تال
    -0.08
     одно
    -0.08
    POSITIVE LOGITS
    一下
    0.09
     relationship
    0.08
    relationship
    0.08
     поведения
    0.08
    Inspect
    0.08
    Relationship
    0.08
    Transit
    0.08
     iw
    0.08
    Manip
    0.07
     подробнее
    0.07
    Act Density 0.030%

    No Known Activations