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

    Neuronpedia

    INDEX
    Explanations

    numeric data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     服务
    0.59
    服务
    0.57
    प्रेम
    0.46
    的服务
    0.46
    女主
    0.46
     गुम
    0.46
     කර
    0.46
    门户
    0.46
     váll
    0.45
     Christchurch
    0.45
    POSITIVE LOGITS
     integer
    1.28
     integers
    1.09
    integer
    1.05
    整数
    1.05
     decimal
    1.04
    Integer
    1.02
     Integer
    0.99
     fractional
    0.89
    decimal
    0.89
     decimals
    0.87
    Act Density 0.174%

    No Known Activations