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

    Neuronpedia

    INDEX
    Explanations

    group

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    boa
    -0.07
     declining
    -0.07
    663
    -0.07
    .getTitle
    -0.07
     строитель
    -0.06
     Qualität
    -0.06
    calling
    -0.06
     долж
    -0.06
     nurturing
    -0.06
    films
    -0.06
    POSITIVE LOGITS
    노출
    0.07
     محیط
    0.07
     Paige
    0.06
     fwrite
    0.06
    atie
    0.06
    HandlerContext
    0.06
    这些
    0.06
    bral
    0.06
    idenav
    0.06
    ่อส
    0.06
    Act Density 0.008%

    No Known Activations