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

    Neuronpedia

    INDEX
    Explanations

    affirmative or negative responses to questions

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

    conversational affirmations and negations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    messageInfo
    -0.59
    出版年
    -0.54
    enderror
    -0.54
    mybatisplus
    -0.53
     GenerationType
    -0.52
    msgSender
    -0.49
    romolecules
    -0.48
     Blogging
    -0.48
     bağlantılar
    -0.48
    -0.47
    POSITIVE LOGITS
    Derp
    0.34
    UnsafeEnabled
    0.34
    xase
    0.33
    KURZBESCHREIBUNG
    0.30
     économies
    0.29
     tatuagens
    0.29
     crianças
    0.28
    ◄
    0.28
     económico
    0.28
     arquitecto
    0.28
    Act Density 0.076%

    No Known Activations