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

    Neuronpedia

    INDEX
    Explanations

    verbs of saying or asking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.28
     প্রক্রিয়া
    0.22
     ¹
    0.22
    家伙
    0.22
     कद
    0.22
     i
    0.21
     oth
    0.21
    ুষ্ট
    0.21
    㹮
    0.21
    ০
    0.21
    POSITIVE LOGITS
     abiert
    0.31
     politely
    0.31
     loudly
    0.30
    Enqueue
    0.28
    ("
    0.28
     excitedly
    0.27
    ٨
    0.25
     públic
    0.25
     jokingly
    0.25
     öffentlich
    0.25
    Act Density 0.198%

    No Known Activations