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

    Neuronpedia

    INDEX
    Explanations

    create new object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carcinomas
    0.81
     Prussians
    0.73
    풉
    0.72
     excreted
    0.72
     LMFBR
    0.71
    可以看出
    0.71
    Break
    0.71
    상이
    0.70
     insufficiency
    0.70
     preservatives
    0.69
    POSITIVE LOGITS
    e
    0.91
    able
    0.87
    िंग
    0.84
    ing
    0.77
    د
    0.75
    eer
    0.74
    не
    0.74
    ece
    0.74
    了一个
    0.72
    ings
    0.68
    Act Density 0.031%

    No Known Activations