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

    Neuronpedia

    INDEX
    Explanations

    requests about sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dwind
    1.27
     anxiously
    1.26
     جت
    1.24
    ਼
    1.23
    виси
    1.21
    ς
    1.18
    ில்லி
    1.17
    ல்கள்
    1.17
    ו
    1.13
    σεις
    1.11
    POSITIVE LOGITS
    िक
    1.61
     dotycz
    1.37
    на
    1.33
    woman
    1.29
     만들기
    1.29
    nep
    1.27
    ش
    1.25
    nse
    1.22
    服用
    1.20
     sabia
    1.19
    Act Density 0.276%

    No Known Activations