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

    Neuronpedia

    INDEX
    Explanations

    availability and interfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kenya
    0.53
     ܐ
    0.52
     הב
    0.49
     pacif
    0.48
     பாம்ப
    0.47
     Rohingya
    0.46
     ११
    0.46
     Oceania
    0.46
     Galapagos
    0.46
     Weibo
    0.46
    POSITIVE LOGITS
     realizan
    0.48
    大型
    0.46
     कर्मचारियों
    0.45
    此次
    0.44
     aumenta
    0.43
    تد
    0.42
    Show
    0.41
    t
    0.41
     increases
    0.41
          
    0.40
    Act Density 0.001%

    No Known Activations