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

    Neuronpedia

    INDEX
    Explanations

    URL and date labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hospitality
    1.65
     neutrons
    1.61
     celebrations
    1.60
     astrophysics
    1.60
     systematics
    1.59
     dignitaries
    1.57
     jewels
    1.57
     pulleys
    1.57
     Attractions
    1.56
    Honey
    1.55
    POSITIVE LOGITS
    钊
    1.35
     соеди
    1.20
    ه‌های
    1.08
     redes
    1.05
    應
    1.04
     alam
    1.02
     началом
    1.01
    擬
    1.00
    0
    0.99
    join
    0.97
    Act Density 0.078%

    No Known Activations