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

    Neuronpedia

    INDEX
    Explanations

    public function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙨
    1.32
    𝙣
    1.18
    в
    1.18
     astring
    1.17
    st
    1.12
    𝙪
    1.11
    𝙩
    1.10
    𝙘
    1.09
     vain
    1.07
    ך
    1.06
    POSITIVE LOGITS
    Сма
    1.10
     सुना
    1.07
    g
    1.07
    Routine
    1.05
    exhaustive
    1.05
     аутохтони
    1.05
    равни
    1.05
     aliphatic
    1.04
    ях
    1.02
    お子
    1.01
    Act Density 0.002%

    No Known Activations