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

    Neuronpedia

    INDEX
    Explanations

    years in the future

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحركة
    0.42
     दर्जन
    0.40
     文章
    0.40
    陉
    0.39
    Ҥ
    0.39
     Magdal
    0.38
    一生
    0.38
    前期
    0.38
     guère
    0.38
     perplexing
    0.38
    POSITIVE LOGITS
     exactly
    0.55
     Exactly
    0.55
     equal
    0.53
     future
    0.50
    Exactly
    0.49
     exactamente
    0.48
     installments
    0.47
    将来
    0.46
    exactly
    0.45
     Periods
    0.45
    Act Density 0.002%

    No Known Activations