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

    Neuronpedia

    INDEX
    Explanations

    terms related to political oppression and human rights violations

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

    Political parties/organizations

    np_acts-logits-general · gemini-2.0-flash

    political parties and leaders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Neighbors
    -0.57
     voisins
    -0.48
     neighbors
    -0.47
    étit
    -0.45
     neighbor
    -0.45
    ContextHolder
    -0.44
     mignon
    -0.44
    居民
    -0.44
    neighbor
    -0.44
    illus
    -0.43
    POSITIVE LOGITS
     party
    1.05
     leadership
    0.90
     branch
    0.83
     Party
    0.81
    party
    0.81
     membership
    0.81
     delegates
    0.80
     PARTY
    0.79
     branches
    0.79
    Party
    0.78
    Act Density 0.211%

    No Known Activations