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

    Neuronpedia

    INDEX
    Explanations

    code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quelconque
    0.22
     nutritive
    0.18
     stoichi
    0.18
     scompar
    0.18
     vacun
    0.18
     vaginalis
    0.18
    黢
    0.18
     viande
    0.18
    冨
    0.18
     habeas
    0.17
    POSITIVE LOGITS
    first
    0.28
    if
    0.27
    os
    0.25
     first
    0.25
    Firstly
    0.25
    首先
    0.24
    u
    0.24
    #
    0.23
     首先
    0.23
    まずは
    0.23
    Act Density 0.588%

    No Known Activations