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

    Neuronpedia

    INDEX
    Explanations

    self-referential systems

    np_max-act-logits · gemini-2.0-flash

    Mentions of database table operations—especially self-joins and queries combining or comparing table rows.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     ú
    -0.07
     compiling
    -0.07
     ace
    -0.07
    ‌گذ
    -0.07
     الن
    -0.07
     mulheres
    -0.06
     тела
    -0.06
     approved
    -0.06
     co
    -0.06
     worse
    -0.06
    POSITIVE LOGITS
    、それ
    0.07
    caler
    0.06
    ,is
    0.06
    _Total
    0.06
    esi
    0.06
    .clientHeight
    0.06
    -fw
    0.06
    _fu
    0.06
     CHK
    0.06
    ….↵↵
    0.06
    Act Density 0.090%

    No Known Activations