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

    Neuronpedia

    INDEX
    Explanations

    complex systems and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     حجت
    0.45
    reflectionMap
    0.44
     ใบ
    0.43
     perror
    0.41
     punishment
    0.40
    Mie
    0.39
    MDET
    0.39
    ]}\
    0.39
     }}
    0.38
     المعاد
    0.38
    POSITIVE LOGITS
    FA
    0.45
     centralised
    0.43
    added
    0.43
     cố
    0.41
     investimentos
    0.41
     centralized
    0.41
     digitalisation
    0.41
     femenino
    0.40
    واصل
    0.39
     formalized
    0.39
    Act Density 0.001%

    No Known Activations