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

    Neuronpedia

    INDEX
    Explanations

    retrospective analysis and testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aries
    0.49
    ies
    0.48
    ise
    0.48
    es
    0.48
    ials
    0.48
     balance
    0.47
    arten
    0.47
     Balance
    0.46
    ists
    0.46
    ash
    0.45
    POSITIVE LOGITS
    Retro
    0.60
    ेंगू
    0.50
     retro
    0.48
     информа
    0.48
     запи
    0.47
     анализа
    0.46
     οικονομ
    0.46
     потреб
    0.46
     бума
    0.46
     анализ
    0.45
    Act Density 0.013%

    No Known Activations