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

    Neuronpedia

    INDEX
    Explanations

    plt.grid(True)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    0.38
     उपभो
    0.37
    tissue
    0.37
    ziej
    0.37
     Tissue
    0.36
     discordant
    0.36
     incurred
    0.35
    Escolh
    0.35
     टिश्यू
    0.35
    кульп
    0.34
    POSITIVE LOGITS
     lw
    0.59
    lw
    0.58
     ls
    0.57
     linewidth
    0.52
    linewidth
    0.50
     LW
    0.50
    LW
    0.50
     .-
    0.50
    ls
    0.49
     Lin
    0.49
    Act Density 0.002%

    No Known Activations