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

    Neuronpedia

    INDEX
    Explanations

    next door or adjacent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.83
     он
    0.75
     Он
    0.70
     he
    0.69
    о
    0.64
     He
    0.62
      
    0.62
    А
    0.61
     А
    0.58
     Время
    0.56
    POSITIVE LOGITS
    <unused1840>
    1.16
    <unused1776>
    1.11
    <unused470>
    1.10
    <unused614>
    1.09
    <unused1875>
    1.09
    <unused307>
    1.09
    <unused2103>
    1.09
    <unused462>
    1.08
    <unused1856>
    1.08
    <unused647>
    1.07
    Act Density 0.000%

    No Known Activations