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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers and positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izlik
    0.66
     முழுவதும்
    0.66
    ഗാ
    0.66
     முழுக்க
    0.64
    PURE
    0.64
    メンズ
    0.63
    ıklı
    0.63
    coons
    0.63
    bruk
    0.63
    maire
    0.63
    POSITIVE LOGITS
     fourth
    3.79
     fifth
    3.71
     sixth
    3.71
     third
    3.65
     seventh
    3.61
     ninth
    3.47
    fourth
    3.39
     eighth
    3.34
    third
    3.29
    第
    3.28
    Act Density 0.210%

    No Known Activations