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

    Neuronpedia

    INDEX
    Explanations

    numbers, symbols, and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ohar
    0.41
    %",
    0.40
    டுக
    0.38
    '",
    0.38
     """",
    0.37
    නු
    0.36
    annon
    0.36
    شک
    0.36
    {}",
    0.36
     yüzde
    0.35
    POSITIVE LOGITS
     rame
    0.38
    ⬥
    0.38
     Worldwide
    0.38
    㕫
    0.37
    哴
    0.37
     Exact
    0.36
    Worldwide
    0.36
     favorites
    0.36
    bordered
    0.36
    逶
    0.36
    Act Density 0.001%

    No Known Activations