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

    Neuronpedia

    INDEX
    Explanations

    words related to "corruption" or "corrupt" governance themes

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

    Following "Cor" or "cor"

    np_acts-logits-general · gemini-2.0-flash

    cor followed by various suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.80
    onViewCreated
    -0.68
    ⓧ
    -0.67
    fromnode
    -0.65
    BeginContext
    -0.62
    IContainer
    -0.60
     nonatomic
    -0.58
    UnknownFieldSet
    -0.57
     Cancelar
    -0.56
     wiederum
    -0.54
    POSITIVE LOGITS
     Anglais
    0.52
    relative
    0.51
     anglais
    0.48
     kor
    0.46
     Cor
    0.46
    rupted
    0.45
     jLabel
    0.45
    MLLoader
    0.45
     cor
    0.44
     Kor
    0.44
    Act Density 0.102%

    No Known Activations