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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    environments
    -0.06
    _Work
    -0.06
     OID
    -0.06
    ğü
    -0.06
    inde
    -0.06
    vang
    -0.06
     Contents
    -0.06
    /book
    -0.06
    MenuBar
    -0.06
    entityManager
    -0.06
    POSITIVE LOGITS
     Kasım
    0.08
    $page
    0.07
     deducted
    0.07
    дон
    0.07
     Ignore
    0.06
    Project
    0.06
     Київ
    0.06
     Stories
    0.06
    .Promise
    0.06
     isLoading
    0.06
    Act Density 0.046%

    No Known Activations