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

    Neuronpedia

    INDEX
    Explanations

    inspection requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    infeld
    0.45
     воен
    0.44
     উড়
    0.43
     anda
    0.42
    ၵ
    0.41
    ӓ
    0.41
    Additionally
    0.41
     ड्रग
    0.41
     ankaŭ
    0.41
     فوجی
    0.40
    POSITIVE LOGITS
     Electroly
    0.40
    🍞
    0.40
    خیص
    0.39
     recessed
    0.38
     Int
    0.38
     Trit
    0.38
    㳓
    0.38
    بت
    0.37
    Instr
    0.37
     recueill
    0.37
    Act Density 0.001%

    No Known Activations