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

    Neuronpedia

    INDEX
    Explanations

    limit expressions with x and y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     брен
    0.71
    俱乐部
    0.67
    营销
    0.67
    服务
    0.66
    融资
    0.65
    团队
    0.64
    资本
    0.63
    运营
    0.63
     финанси
    0.62
    货币
    0.61
    POSITIVE LOGITS
     x
    0.71
     infinitely
    0.69
     axis
    0.66
     regions
    0.65
     negative
    0.63
     point
    0.61
     boundary
    0.61
     infinite
    0.61
    0
    0.61
     points
    0.60
    Act Density 0.102%

    No Known Activations