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

    Neuronpedia

    INDEX
    Explanations

    snippets from lists of things and their descriptions or origins.

    oai_token-act-pair · gemini-2.0-flash

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ::_('
    -0.56
    rung
    -0.41
    "
    -0.40
    <bos>
    -0.40
    worse
    -0.40
     chỗ
    -0.39
     пока
    -0.39
     Führung
    -0.39
    ABUL
    -0.39
     mà
    -0.39
    POSITIVE LOGITS
    featureID
    0.87
     uſed
    0.79
     تضيفلها
    0.75
    AndEndTag
    0.74
     utafitiHapana
    0.73
     myſelf
    0.72
     transfieras
    0.72
     ویکی‌پدی
    0.72
    AsUp
    0.72
     متعلقه
    0.70
    Act Density 1.425%

    No Known Activations