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

    Neuronpedia

    INDEX
    Explanations

    but followed by a warning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     層
    0.45
     निर्
    0.45
     పూర్తిగా
    0.43
     LAYER
    0.41
     STADT
    0.41
     שכ
    0.41
     MANUFACTURING
    0.40
     fieldContext
    0.40
    ụp
    0.40
     폐
    0.40
    POSITIVE LOGITS
     benefits
    0.43
     knowledgeable
    0.42
     Benefits
    0.42
    जों
    0.41
     ওখানে
    0.41
     optimized
    0.41
     beneficios
    0.41
     rencontré
    0.40
     équipé
    0.40
    参考
    0.39
    Act Density 0.005%

    No Known Activations