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

    Neuronpedia

    INDEX
    Explanations

    control and pressure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Al
    0.51
    សុ
    0.48
     Nar
    0.47
     Oil
    0.46
     InMemory
    0.45
     Ot
    0.44
     El
    0.43
     Mayor
    0.43
     Ez
    0.43
     N
    0.43
    POSITIVE LOGITS
    调度
    0.48
     वाटते
    0.47
    vrir
    0.45
    ારે
    0.44
    ﹑
    0.43
    чивать
    0.42
     वेळा
    0.41
    beri
    0.41
    cidr
    0.41
    scm
    0.41
    Act Density 0.005%

    No Known Activations