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

    Neuronpedia

    INDEX
    Explanations

    Optimal/optimization related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itemList
    0.43
     exponential
    0.42
    ıkl
    0.41
    不足
    0.41
     indispensables
    0.41
     vegetarians
    0.40
     immigrants
    0.40
     venom
    0.40
     insufficiency
    0.40
    ኙ
    0.40
    POSITIVE LOGITS
    Wars
    0.40
     оптима
    0.40
    Stri
    0.39
    Optimal
    0.38
    萑
    0.38
     Wars
    0.37
    షణ
    0.37
    Defaults
    0.37
    优化
    0.36
    Obs
    0.36
    Act Density 0.000%

    No Known Activations