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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "don't" and related phrases indicating negation or disagreement

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

    expressing opinions in discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.75
    IndentedString
    -0.73
     miniaturka
    -0.71
     jadx
    -0.71
     AssemblyCulture
    -0.71
     Biôgrafia
    -0.69
    хьтан
    -0.68
    Personensuche
    -0.68
     мәкал
    -0.66
     ſeine
    -0.66
    POSITIVE LOGITS
     discussion
    0.32
     ideas
    0.31
    ren
    0.31
    post
    0.30
     وجه
    0.29
    onResume
    0.29
     discussions
    0.28
    SuspendLayout
    0.28
    am
    0.28
    ja
    0.28
    Act Density 0.126%

    No Known Activations