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

    Neuronpedia

    INDEX
    Explanations

    followed by, accompanied by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তাহ
    0.82
     basiert
    0.73
     spricht
    0.73
    Bran
    0.73
    ISTA
    0.73
    QueueMutex
    0.72
     Überblick
    0.70
     тыс
    0.70
     పేరు
    0.70
    %%%%%%%%%%%%%
    0.69
    POSITIVE LOGITS
     supplementation
    1.14
     accompaniment
    1.10
     complement
    1.01
     nhau
    1.00
     compliment
    1.00
     complementing
    0.99
     accompany
    0.98
     complementary
    0.98
     obligatory
    0.97
     compliments
    0.96
    Act Density 0.146%

    No Known Activations