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

    Neuronpedia

    INDEX
    Explanations

    cost of living or lore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gate
    0.61
    ing
    0.55
     Gateway
    0.52
     City
    0.52
     Esc
    0.50
     Head
    0.49
     Alert
    0.48
     Tarn
    0.48
     Co
    0.48
     Payment
    0.47
    POSITIVE LOGITS
    ید
    0.49
    ([],
    0.47
    रसा
    0.43
     superflu
    0.42
    란
    0.42
    ('',
    0.41
    Energie
    0.40
     edific
    0.40
    Unsere
    0.40
    Conceptual
    0.40
    Act Density 0.001%

    No Known Activations