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

    Neuronpedia

    INDEX
    Explanations

    ratios and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Стаўкі
    0.41
    Friday
    0.40
    Kind
    0.40
    Newcastle
    0.40
    Yeah
    0.39
    8
    0.39
    Prime
    0.39
    Frederick
    0.39
    ඔ
    0.38
    Dave
    0.38
    POSITIVE LOGITS
     всё
    0.42
     Guid
    0.42
     guia
    0.41
    ưu
    0.38
    amientos
    0.38
     mè
    0.38
    스가
    0.38
     glimpses
    0.38
     courants
    0.38
     mer
    0.38
    Act Density 0.000%

    No Known Activations