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

    Neuronpedia

    INDEX
    Explanations

    fresh produce and herbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     théorème
    0.54
     untrue
    0.53
     Congrès
    0.53
     écrire
    0.52
     বাস্তবতা
    0.51
    哐
    0.50
    手表
    0.50
     bardziej
    0.50
     oameni
    0.49
     রেলপথ
    0.49
    POSITIVE LOGITS
    ness
    0.59
    da
    0.55
    ton
    0.53
     and
    0.52
    र्न
    0.49
     fresh
    0.49
     produce
    0.49
    rogen
    0.49
    на
    0.49
     freshwater
    0.49
    Act Density 0.009%

    No Known Activations