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

    Neuronpedia

    INDEX
    Explanations

    numbers or specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    1.32
    ে
    1.30
    e
    1.28
    et
    1.18
    েয়
    1.16
     vaan
    1.15
     L
    1.14
    ey
    1.14
    leden
    1.13
    zelfde
    1.13
    POSITIVE LOGITS
    ը
    1.45
    3
    1.45
     a
    1.40
    من
    1.39
    ع
    1.38
    1.33
     electrónicos
    1.27
    ﻮ
    1.25
    2
    1.24
    НА
    1.23
    Act Density 0.569%

    No Known Activations