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

    Neuronpedia

    INDEX
    Explanations

    inventory is key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Electronic
    0.46
    uated
    0.46
     elektronic
    0.46
     Electronics
    0.45
     étroites
    0.45
     বিল্ডিং
    0.44
    かもしれませんが
    0.43
    建物
    0.43
    κέ
    0.42
     Bldg
    0.41
    POSITIVE LOGITS
     hemolysis
    0.44
    rant
    0.41
    uencia
    0.41
    ยายาม
    0.41
     servant
    0.40
    aseña
    0.40
     confusión
    0.40
    serv
    0.39
    gpt
    0.39
     crise
    0.38
    Act Density 0.001%

    No Known Activations