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

    Neuronpedia

    INDEX
    Explanations

    sybibuns, Kobolds, Goblin, Robotics, Karabits, ABAP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ν
    1.41
    1
    1.38
    4
    1.20
    고
    1.20
    with
    1.17
    ع
    1.17
     the
    1.16
    る
    1.15
    १
    1.12
    you
    1.11
    POSITIVE LOGITS
    心
    1.34
     يع
    1.20
    ి
    1.18
     هي
    1.15
     profiter
    1.14
    يد
    1.13
    ة
    1.12
     jsou
    1.06
     verein
    1.03
    用
    1.02
    Act Density 0.526%

    No Known Activations