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

    Neuronpedia

    INDEX
    Explanations

    still, though, require

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vielfält
    0.53
    ęcz
    0.53
    为什么要
    0.50
     gooey
    0.49
     chcesz
    0.46
    вары
    0.45
     Tackle
    0.44
    rotl
    0.43
     отмечает
    0.43
    ClFN
    0.43
    POSITIVE LOGITS
    と
    0.45
    काश
    0.43
     प्रभारी
    0.41
     शी
    0.41
    VW
    0.41
     ਹ
    0.41
    確定
    0.41
     handc
    0.41
     तार
    0.41
    ハリ
    0.40
    Act Density 0.005%

    No Known Activations