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

    Neuronpedia

    INDEX
    Explanations

    ARRAY REPORTING

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    0.57
     full
    0.54
     BA
    0.54
     black
    0.52
     year
    0.52
     splash
    0.51
     Middle
    0.50
     l
    0.49
    lect
    0.49
    at
    0.49
    POSITIVE LOGITS
     sucks
    0.56
    有趣
    0.54
    kjhtml
    0.53
    事物
    0.52
    стям
    0.50
    ソース
    0.49
    Emma
    0.48
     הזה
    0.48
     postérieurs
    0.48
    တတ်
    0.47
    Act Density 0.000%

    No Known Activations