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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations and arithmetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    効率
    0.39
     효율
    0.39
     effiz
    0.38
    Efficient
    0.38
     efficient
    0.37
     anisotropic
    0.36
     efficiently
    0.36
     Gitar
    0.35
    Anthrop
    0.35
     guerrilla
    0.35
    POSITIVE LOGITS
     math
    1.65
     arithmetic
    1.61
     maths
    1.51
     calculations
    1.49
     математи
    1.48
     calculation
    1.46
    算
    1.46
     गणित
    1.45
    計算
    1.44
    数学
    1.44
    Act Density 0.029%

    No Known Activations