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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     radians
    0.79
    ɹ
    0.74
     Auburn
    0.74
    স্ফ
    0.73
    ennial
    0.73
     \|
    0.72
     inches
    0.72
    是如何
    0.72
    卓越
    0.72
     ander
    0.71
    POSITIVE LOGITS
     các
    1.44
     Việt
    1.35
     dễ
    1.32
     cùng
    1.25
     Liên
    1.25
     đều
    1.17
     nhiều
    1.17
     để
    1.17
     vừa
    1.17
     vào
    1.16
    Act Density 0.069%

    No Known Activations