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

    Neuronpedia

    INDEX
    Explanations

    alcoholic beverages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     πολι
    0.36
     siy
    0.35
    欤
    0.34
    िसिटी
    0.34
     प्रतिरक्षा
    0.34
     alterar
    0.33
     schimb
    0.33
    abend
    0.33
    ථා
    0.32
    ಕ್ರಮ
    0.32
    POSITIVE LOGITS
     seabed
    0.42
     bronze
    0.41
     dunes
    0.40
     સંદ
    0.38
     cognac
    0.38
     दक्ष
    0.38
     surfactants
    0.37
     endpoints
    0.37
     finca
    0.37
     Musée
    0.37
    Act Density 0.003%

    No Known Activations