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

    Neuronpedia

    INDEX
    Explanations

    all-inclusive or all necessary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AIRMAN
    0.40
     такие
    0.38
     সেসব
    0.38
     таких
    0.37
     शेखर
    0.37
     이러한
    0.37
    물의
    0.36
    ázky
    0.36
     goalt
    0.36
     assertFalse
    0.35
    POSITIVE LOGITS
     rooms
    0.58
     utilities
    0.56
     facilities
    0.55
     appliances
    0.52
     fasilitas
    0.51
     amenities
    0.51
     utensils
    0.51
     condiments
    0.50
    设施
    0.50
     furniture
    0.50
    Act Density 0.003%

    No Known Activations