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

    Neuronpedia

    INDEX
    Explanations

    sentences and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polinom
    0.97
    裆
    0.89
     ilegal
    0.88
     υπάρχει
    0.87
     ಎರಡ
    0.86
    भाविक
    0.86
    heatmap
    0.86
     diberikan
    0.85
    缓存
    0.85
    จะต้อง
    0.84
    POSITIVE LOGITS
     food
    0.90
     each
    0.79
     pairs
    0.77
    ically
    0.74
     nouns
    0.74
     wonders
    0.74
    یں۔
    0.71
     sentences
    0.71
    osyl
    0.71
     words
    0.70
    Act Density 0.424%

    No Known Activations