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

    Neuronpedia

    INDEX
    Explanations

    latest, newest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     предлага
    0.45
     sierpnia
    0.43
    0.43
    വന
    0.43
     لیکن
    0.42
     целях
    0.42
    鞑
    0.41
    avgsalary
    0.41
     menawarkan
    0.41
     culturas
    0.41
    POSITIVE LOGITS
    最新
    0.70
     latest
    0.66
    Latest
    0.59
     newest
    0.56
     Latest
    0.53
    latest
    0.53
     最新
    0.48
    最新的
    0.43
     fatigue
    0.39
     PRE
    0.37
    Act Density 0.000%

    No Known Activations