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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their actions

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

    Malaysian political discourse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     django
    -0.34
    회
    -0.32
    DeleteBehavior
    -0.32
     obro
    -0.29
     berpikir
    -0.27
    tried
    -0.27
     PeEnEo
    -0.27
     sø
    -0.26
     Ved
    -0.26
    significant
    -0.25
    POSITIVE LOGITS
    Malaysia
    0.83
     Lumpur
    0.82
     Malaysian
    0.79
     Malaysia
    0.76
    BASEPATH
    0.71
    0.68
     LUMP
    0.66
     EconPapers
    0.66
    Malay
    0.64
    UALA
    0.64
    Act Density 0.199%

    No Known Activations