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

    Neuronpedia

    INDEX
    Explanations

    led her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     интерфей
    0.46
     =~
    0.44
    ляция
    0.43
    行李
    0.43
     essentially
    0.42
     ৬
    0.41
     говорили
    0.40
    0.40
     н
    0.40
    estabelecimento
    0.40
    POSITIVE LOGITS
     Growers
    0.49
     Forced
    0.48
     Familie
    0.48
     growers
    0.48
     Watering
    0.48
     Observing
    0.47
     Amish
    0.47
     Ecosystem
    0.46
     them
    0.46
     Sustainable
    0.46
    Act Density 0.002%

    No Known Activations