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

    Neuronpedia

    INDEX
    Explanations

    references to rulings and political classes or parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ruling class or clique

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.79
     témoig
    -0.60
     cellspacing
    -0.60
    IsContent
    -0.59
     AspNetCore
    -0.59
     argint
    -0.58
    Carbo
    -0.57
     Préférences
    -0.57
    azaki
    -0.57
     verſch
    -0.57
    POSITIVE LOGITS
     ruling
    2.08
     Ruling
    1.84
    ruling
    1.71
     rulings
    1.30
    ULING
    0.90
    ruled
    0.78
     Rul
    0.78
     ruled
    0.77
     governing
    0.73
     rulers
    0.68
    Act Density 0.007%

    No Known Activations