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

    Neuronpedia

    INDEX
    Explanations

    that are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noin
    1.22
     your
    1.16
    let
    1.09
    it
    1.08
     njegov
    1.06
     territory
    1.06
    le
    1.05
     to
    1.02
    es
    1.01
     ovaj
    1.01
    POSITIVE LOGITS
    рные
    1.39
    рованные
    1.33
    ^\
    1.27
     slanted
    1.26
     जिनमें
    1.26
     diminish
    1.26
    were
    1.25
    ᴗ
    1.24
    mselves
    1.24
     banded
    1.22
    Act Density 0.439%

    No Known Activations