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

    Neuronpedia

    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     personer
    0.29
    စ္စည်း
    0.28
    ᕇ
    0.27
    𒍝
    0.27
    গ্রেস
    0.27
     unterstützen
    0.27
    رسٹ
    0.26
     ব্যবহার
    0.25
     युवकों
    0.25
     modList
    0.25
    POSITIVE LOGITS
    0.35
    The
    0.30
    ə
    0.27
     The
    0.25
    á
    0.24
     \
    0.23
    ø
    0.23
     premiered
    0.23
    mathrm
    0.22
     tři
    0.22
    Act Density 0.222%

    No Known Activations