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

    Neuronpedia

    INDEX
    Explanations

    improves and efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     splendid
    0.52
     教育
    0.49
     ብ
    0.49
     blossomed
    0.49
     క
    0.48
     disgraced
    0.48
     spirited
    0.48
     eğitim
    0.46
     знамени
    0.46
     flourished
    0.46
    POSITIVE LOGITS
    app
    0.55
    if
    0.52
    Ⲙ
    0.48
    arr
    0.48
    metrics
    0.47
    munder
    0.46
     Preferences
    0.46
    amme
    0.45
    둰
    0.45
    window
    0.45
    Act Density 0.000%

    No Known Activations