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

    Neuronpedia

    INDEX
    Explanations

    Okay, let's break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ET
    1.33
    RY
    1.28
    IN
    1.23
     että
    1.20
     或者
    1.19
    쎄
    1.16
    ﯼ
    1.13
     również
    1.12
    TING
    1.11
     Temmuz
    1.09
    POSITIVE LOGITS
    ر
    1.45
    ق
    1.35
    га
    1.27
    ↵
    1.24
    garde
    1.20
    geschichte
    1.18
    ন
    1.16
    ない
    1.16
    g
    1.16
    乑
    1.16
    Act Density 0.501%

    No Known Activations