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

    Neuronpedia

    INDEX
    Explanations

    Sustainable Development Goals (SDGs)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.52
     ổ
    0.48
    τ
    0.48
    uh
    0.48
     જ્યારે
    0.47
     pracuje
    0.47
    管理局
    0.46
    ς
    0.46
     za
    0.45
    勤務
    0.45
    POSITIVE LOGITS
    IN
    0.54
    ומי
    0.52
     attainment
    0.52
     imbalances
    0.50
     SDGs
    0.50
    лся
    0.48
     betterment
    0.48
     inequities
    0.47
    НЫ
    0.46
    ূল
    0.45
    Act Density 0.001%

    No Known Activations