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

    Neuronpedia

    INDEX
    Explanations

    doing or what can be done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tivemos
    0.37
    會有
    0.35
    ந
    0.35
     setError
    0.33
    ណ្ឌ
    0.33
     Necessity
    0.33
     somente
    0.32
     चट्ट
    0.32
     Sum
    0.32
     кода
    0.32
    POSITIVE LOGITS
     doing
    0.88
     accomplish
    0.84
    Doing
    0.80
     Doing
    0.76
     lakukan
    0.73
    doing
    0.73
     accomplishes
    0.71
     accomplishing
    0.68
     делать
    0.67
     do
    0.65
    Act Density 0.096%

    No Known Activations