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

    Neuronpedia

    INDEX
    Explanations

    code sections with labels

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    afka
    -0.07
    åŀ
    -0.06
     беÑģп
    -0.06
    kit
    -0.06
    á»ı
    -0.06
    itors
    -0.06
    zych
    -0.06
     distr
    -0.06
    ote
    -0.06
    .gdx
    -0.06
    POSITIVE LOGITS
     section
    0.17
    section
    0.14
     subsection
    0.14
     sections
    0.13
    -section
    0.13
     Section
    0.12
    .section
    0.11
    Section
    0.11
    (section
    0.11
    _section
    0.10
    Act Density 0.114%

    No Known Activations