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

    Neuronpedia

    INDEX
    Explanations

    good at processing sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    og
    0.47
     T
    0.44
     C
    0.43
    j
    0.42
     L
    0.41
    ex
    0.41
     S
    0.41
    0.41
    ms
    0.40
     Sn
    0.40
    POSITIVE LOGITS
     для
    0.55
     για
    0.45
    สำหรับการ
    0.45
     để
    0.45
     برای
    0.45
    ກັບ
    0.44
     upang
    0.43
     untuk
    0.42
    <unused1049>
    0.42
    ﻝ
    0.41
    Act Density 0.016%

    No Known Activations