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

    Neuronpedia

    INDEX
    Explanations

    strongly urge you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    близи
    0.44
     Tra
    0.43
    rejected
    0.43
    inserted
    0.42
    激活
    0.41
     có
    0.41
     faced
    0.41
    病例
    0.41
     Patient
    0.40
    ناها
    0.40
    POSITIVE LOGITS
     ਅ
    0.48
     чел
    0.47
     протягом
    0.47
     dezelfde
    0.46
     ਇਸ
    0.45
    }}(-
    0.44
     entreprise
    0.44
     distiller
    0.44
     paradigm
    0.44
     मालिक
    0.44
    Act Density 0.001%

    No Known Activations