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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize specific subjects or topics being discussed

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

    asking why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grüsse
    -0.34
    RTGC
    -0.33
    IsMutable
    -0.33
    <_>
    -0.32
    </table>
    -0.31
    .*")]
    -0.31
    ёх
    -0.30
    WithFormat
    -0.30
    )](
    -0.29
    podar
    -0.29
    POSITIVE LOGITS
     Why
    0.61
    Why
    0.60
     why
    0.58
     waarom
    0.56
     ویکی‌پدی
    0.56
    WHY
    0.54
    xase
    0.54
     Waarom
    0.53
    Kenapa
    0.53
    Почему
    0.52
    Act Density 0.015%

    No Known Activations