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

    Neuronpedia

    INDEX
    Explanations

    PCI and CC acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᴛ
    2.60
    ра
    2.58
     vaulted
    2.52
    tevõ
    2.45
    CIP
    2.35
    𝖽
    2.27
    ни
    2.26
    ︎
    2.19
    ट
    2.15
    зи
    2.13
    POSITIVE LOGITS
    tedir
    4.14
    ../../
    4.10
    م
    4.04
    اً
    3.93
    ej
    3.83
    ీ
    3.73
    eh
    3.71
    ে
    3.56
    eur
    3.54
    ei
    3.41
    Act Density 0.055%

    No Known Activations