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

    Neuronpedia

    INDEX
    Explanations

    2023 dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bood
    0.59
     Insight
    0.57
    Heading
    0.57
     Castro
    0.56
     October
    0.55
     Frontiers
    0.55
    nor
    0.55
     abit
    0.54
     sensitivity
    0.53
    Att
    0.53
    POSITIVE LOGITS
    пка
    0.82
     plabic
    0.79
    кая
    0.79
     Bél
    0.76
     कैफ
    0.74
    锰
    0.73
     integers
    0.72
    લ્ડ
    0.71
    のマ
    0.70
     contratto
    0.70
    Act Density 0.015%

    No Known Activations