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

    Neuronpedia

    INDEX
    Explanations

    implementing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ☞
    2.51
    ਰ
    2.24
     overw
    2.24
    是在
    2.20
    দের
    2.19
     équip
    2.18
    식
    2.17
    лки
    2.14
     gaw
    2.13
    ThreadPool
    2.12
    POSITIVE LOGITS
    ead
    2.23
    ൺ
    2.17
    is
    2.16
    عاد
    2.16
    ig
    2.11
    ем
    2.09
    غ
    2.08
    ль
    2.04
    ار
    2.01
    tad
    1.98
    Act Density 0.075%

    No Known Activations