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

    Neuronpedia

    INDEX
    Explanations

    programming structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    group
    0.51
    (
    0.49
    g
    0.49
    \(
    0.48
    全
    0.48
    {
    0.48
    ---
    0.45
    catch
    0.45
    recogn
    0.45
    1
    0.45
    POSITIVE LOGITS
     план
    0.54
     χαρακ
    0.54
    <unused593>
    0.52
     оста
    0.52
     రాజ్య
    0.51
     conspiring
    0.51
    शेखर
    0.50
    <unused585>
    0.50
     Ку
    0.50
     নির্দিষ্ট
    0.50
    Act Density 0.000%

    No Known Activations