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

    Neuronpedia

    INDEX
    Explanations

    cost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Att
    -0.07
     çıktı
    -0.07
     üretim
    -0.07
     چت
    -0.07
     voleb
    -0.07
    금
    -0.07
     ör
    -0.06
    ैन
    -0.06
    ぁ
    -0.06
     authentication
    -0.06
    POSITIVE LOGITS
     costing
    0.07
     costs
    0.07
     Worth
    0.06
     Costs
    0.06
     weighs
    0.06
    cost
    0.06
     weigh
    0.06
     moo
    0.06
    Scott
    0.06
     Missing
    0.06
    Act Density 0.041%

    No Known Activations