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

    Neuronpedia

    INDEX
    Explanations

    solving mathematical problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    相当于
    0.73
    採用
    0.72
     quantidades
    0.72
     পৃথিব
    0.72
     envisaged
    0.72
     odpowiedzial
    0.71
    সংস
    0.71
     तात्
    0.69
     পৃথিবীর
    0.68
    ustainable
    0.68
    POSITIVE LOGITS
     graphing
    1.38
     Graph
    1.11
     graphs
    1.10
    Graph
    1.09
     Graphs
    1.09
     factoring
    1.06
     graph
    1.06
     Solving
    1.03
     Identifying
    1.03
     quadratic
    1.03
    Act Density 0.225%

    No Known Activations