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

    Neuronpedia

    INDEX
    Explanations

    individuals, lifespan, Station, status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    0.48
    ไว
    0.44
    雙
    0.43
    ת
    0.42
     uży
    0.42
    双
    0.41
     uso
    0.41
    你需要
    0.41
    نية
    0.41
    _
    0.41
    POSITIVE LOGITS
     knowledge
    0.45
     Radiation
    0.43
     hầu
    0.42
     profound
    0.42
     பொறிய
    0.42
    ையிலும்
    0.41
     lâ
    0.41
     ১৯৪৭
    0.41
     -*-
    0.40
     மேம்ப
    0.40
    Act Density 0.007%

    No Known Activations