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

    Neuronpedia

    INDEX
    Explanations

    golden followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ርስዎ
    0.38
     चांद
    0.38
    gesamt
    0.36
    广大
    0.36
    nfasis
    0.35
     Reactive
    0.35
    ucia
    0.35
     Incorporation
    0.35
    ッサージ
    0.35
     Bourg
    0.34
    POSITIVE LOGITS
     golden
    1.59
    Golden
    1.58
     Golden
    1.55
    golden
    1.49
     गोल्डन
    1.07
    黄金
    0.98
     золо
    0.91
     retriever
    0.85
    Золо
    0.81
     सुनहरा
    0.80
    Act Density 0.011%

    No Known Activations