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

    Neuronpedia

    INDEX
    Explanations

    adding numbers and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    QSpacerItem
    0.40
     केसांना
    0.39
     дворе
    0.38
    ږ
    0.38
     Fittings
    0.37
    汝
    0.37
     строй
    0.37
     encomendas
    0.36
    குதி
    0.36
     amén
    0.35
    POSITIVE LOGITS
    Addition
    1.89
     Addition
    1.81
     addition
    1.74
    addition
    1.74
     subtraction
    1.68
     multiplication
    1.65
     penjumlahan
    1.58
     arithmetic
    1.56
     summation
    1.55
    Subtraction
    1.52
    Act Density 0.141%

    No Known Activations