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

    Neuronpedia

    INDEX
    Explanations

    And connector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jedoch
    0.38
     però
    0.35
     allerdings
    0.33
     हालांकि
    0.32
    υ
    0.32
     واخ
    0.31
    কিন্ত
    0.31
    𝐎
    0.30
     Однако
    0.30
     azonban
    0.30
    POSITIVE LOGITS
    ată
    0.37
    ंगाबाद
    0.35
     là
    0.34
    termilk
    0.33
    quela
    0.33
     ใช่
    0.32
     oczywiście
    0.32
     যদি
    0.32
     когато
    0.32
    скольку
    0.32
    Act Density 0.051%

    No Known Activations