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

    Neuronpedia

    INDEX
    Explanations

    states or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sre
    1.15
    alloc
    1.10
    arbe
    1.10
    upid
    1.07
    HUD
    1.07
    Stars
    1.06
    ઓમાં
    1.05
    IGNED
    1.05
     ASSEM
    1.05
    いきます
    1.04
    POSITIVE LOGITS
    ا
    1.19
     Rita
    1.13
    Melitaea
    1.10
    ള്
    1.10
     sited
    1.04
    র্ষি
    1.04
     Dabei
    1.02
     ट्रू
    1.02
    ਨ
    1.01
     reckoned
    1.01
    Act Density 0.001%

    No Known Activations