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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    运营
    0.41
     veřej
    0.40
    服务
    0.39
    acariy
    0.38
     Öffentlichkeit
    0.38
    营销
    0.37
    的市场
    0.37
    บริการ
    0.37
    基础设施
    0.36
    经纪
    0.36
    POSITIVE LOGITS
     equations
    0.46
     polynomial
    0.45
     integers
    0.44
     values
    0.43
     nonzero
    0.43
     algebraic
    0.43
     parentheses
    0.42
     variables
    0.42
     polynomials
    0.42
     equation
    0.42
    Act Density 0.681%

    No Known Activations