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

    Neuronpedia

    INDEX
    Explanations

    regex delimiters and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ิ
    0.64
    يك
    0.62
    า
    0.61
    እና
    0.59
    ਾ
    0.59
     Snowden
    0.57
    ри
    0.55
    ける
    0.55
    長さ
    0.55
    ικ
    0.55
    POSITIVE LOGITS
    2
    0.77
    9
    0.68
    custom
    0.67
    goods
    0.67
    service
    0.66
    food
    0.66
    field
    0.66
    cell
    0.65
    chart
    0.64
    end
    0.64
    Act Density 0.009%

    No Known Activations