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

    Neuronpedia

    INDEX
    Explanations

    end of quoted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    1.31
    с
    1.16
    ে
    1.14
     انہوں
    1.13
    give
    1.10
     ironically
    1.09
     infuri
    1.09
    ोत्सव
    1.07
    hellip
    1.05
    𝐫
    1.03
    POSITIVE LOGITS
    м
    1.63
    ي
    1.60
    ি
    1.48
    લ
    1.32
    り
    1.29
    %=
    1.25
    мл
    1.23
    слов
    1.22
     Raster
    1.20
    elands
    1.20
    Act Density 0.018%

    No Known Activations