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

    Neuronpedia

    INDEX
    Explanations

    FP, SHA, IP, DDR, Series, d, H

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ইউনিভার্সিটি
    0.42
    aundice
    0.41
    懑
    0.39
    plication
    0.38
    nehmen
    0.38
     Terrorism
    0.38
    سرائيل
    0.38
    глежда
    0.38
    傃
    0.38
    ます
    0.37
    POSITIVE LOGITS
    1
    0.50
    -
    0.49
    ‐
    0.48
    １
    0.46
    III
    0.40
    0.40
    2
    0.39
     III
    0.38
    －
    0.38
    ‑
    0.37
    Act Density 0.076%

    No Known Activations