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
     натураль
    -0.09
    高さ
    -0.09
     Tradition
    -0.09
     национ
    -0.09
     очищ
    -0.09
     flax
    -0.08
    nod
    -0.08
     коллектив
    -0.08
     заболевания
    -0.08
     refreshments
    -0.08
    POSITIVE LOGITS
     billing
    0.12
     Billing
    0.11
    billing
    0.11
    Billing
    0.10
    .billing
    0.10
     quota
    0.10
    优化
    0.10
     Kubernetes
    0.10
     Optimize
    0.10
     optimizing
    0.10
    Act Density 0.008%

    No Known Activations