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

    Neuronpedia

    INDEX
    Explanations

    references to voting and election choices

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

    vote for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aandacht
    -0.41
     coverage
    -0.38
    ContentAlignment
    -0.38
    かけ
    -0.36
     betrek
    -0.36
    MeasureSpec
    -0.35
     Capsule
    -0.34
     bleef
    -0.34
    ecken
    -0.34
     session
    -0.34
    POSITIVE LOGITS
     wireType
    0.64
    choosing
    0.63
    Choosing
    0.59
    Купить
    0.58
     Савезне
    0.56
    AutoModerator
    0.56
     >=",
    0.55
     ModelExpression
    0.54
    DIPSETTING
    0.54
     vote
    0.53
    Act Density 0.012%

    No Known Activations