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

    Neuronpedia

    INDEX
    Explanations

    statistics and business terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    month
    0.43
    𝓶
    0.43
    𝘩
    0.42
    獨立
    0.42
     παιδιά
    0.42
     Сим
    0.42
     नगरपालिका
    0.42
    转化为
    0.42
    expense
    0.41
    𝓱
    0.41
    POSITIVE LOGITS
     which
    0.54
     of
    0.50
     websocket
    0.49
     wich
    0.47
     syph
    0.46
     voces
    0.45
     verticals
    0.45
     uncorrelated
    0.44
     on
    0.43
     that
    0.43
    Act Density 0.000%

    No Known Activations