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

    Neuronpedia

    INDEX
    Explanations

    elements related to geographic locations and paths

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

    Markdown or code snippets

    np_acts-logits-general · gemini-2.0-flash

    this is because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </strong>
    -1.11
     […]
    -0.76
    </h1>
    -0.74
     ddelweddau
    -0.71
    <strong>
    -0.70
    <em>
    -0.67
    <eos>
    -0.61
    ↵↵↵↵
    -0.58
    "><
    -0.56
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.56
    POSITIVE LOGITS
     Савезне
    1.10
    sizeCache
    1.00
    QMetaType
    0.98
    Fordítás
    0.97
     Efq
    0.97
     purpoſe
    0.95
     autorytatywna
    0.95
    OGND
    0.90
     ویکی‌پدی
    0.88
     الرياضيه
    0.88
    Act Density 1.004%

    No Known Activations