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

    Neuronpedia

    INDEX
    Explanations

    arithmetic and mathematical calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    媧
    0.41
     właścic
    0.39
    ेलकम
    0.39
     zapewn
    0.39
     sele
    0.38
     पद्ध
    0.38
     sólo
    0.38
     estrut
    0.37
    বায়
    0.36
    elaar
    0.36
    POSITIVE LOGITS
     math
    0.52
    是多少
    0.51
    math
    0.48
     Calculator
    0.43
     calculator
    0.43
    Calculate
    0.42
     arithmetic
    0.42
     equations
    0.41
     mathematics
    0.41
    9
    0.41
    Act Density 0.078%

    No Known Activations