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

    Neuronpedia

    INDEX
    Explanations

    numbers in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    两者
    1.36
     둘
    1.20
     beiden
    1.20
     Two
    1.19
     दोघा
    1.18
     begge
    1.14
    Two
    1.11
    兩人
    1.09
     keduanya
    1.09
     இரண்ட
    1.08
    POSITIVE LOGITS
     nine
    3.96
     eight
    3.86
     seven
    3.73
     twelve
    3.73
     sixteen
    3.59
     fifteen
    3.59
     eleven
    3.57
     fourteen
    3.56
     thirteen
    3.55
     ten
    3.52
    Act Density 0.604%

    No Known Activations