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

    Neuronpedia

    INDEX
    Explanations

    GSD documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    коло
    0.94
    enegro
    0.90
    يران
    0.86
     ಕರ್
    0.84
    トップ
    0.84
     її
    0.83
    old
    0.81
    ポン
    0.80
     цветов
    0.80
     його
    0.80
    POSITIVE LOGITS
     দিকের
    1.06
     sided
    1.01
    zī
    0.98
    Voilà
    0.97
    یتی
    0.97
     hangi
    0.95
    ICY
    0.94
    সংখ্যক
    0.94
     themed
    0.93
     attempt
    0.92
    Act Density 0.672%

    No Known Activations