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

    Neuronpedia

    INDEX
    Explanations

    modifier followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hưởng
    0.49
    中标
    0.47
    acknowledge
    0.46
    示した
    0.46
    measured
    0.46
    监测
    0.45
    isión
    0.44
    ມ
    0.44
    liver
    0.43
    自
    0.43
    POSITIVE LOGITS
     ultima
    0.48
     materi
    0.46
    Jud
    0.46
     אפ
    0.45
     애플
    0.45
    логі
    0.45
     অ্যাপার্টমেন্ট
    0.45
     Premises
    0.45
     motto
    0.44
     zum
    0.44
    Act Density 0.000%

    No Known Activations