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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to monitoring and assessment

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

    own ancestry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    berdayakan
    -0.74
     ویکی‌پدی
    -0.74
    +#+#
    -0.64
     utafitiHapana
    -0.64
    RenderAtEndOf
    -0.61
     Мексичка
    -0.60
     arşivlendi
    -0.60
     يتيمه
    -0.58
    ſammen
    -0.57
     Réponses
    -0.57
    POSITIVE LOGITS
     hot
    0.49
     Google
    0.42
     students
    0.41
     bad
    0.40
     cooking
    0.40
     major
    0.40
     cold
    0.40
     traditional
    0.40
     or
    0.39
     the
    0.39
    Act Density 0.060%

    No Known Activations