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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /I
    -0.07
     occup
    -0.07
     %,
    -0.06
     mandated
    -0.06
    .bundle
    -0.06
     Clip
    -0.06
    .link
    -0.06
    /********
    -0.06
    idlo
    -0.06
     beyond
    -0.06
    POSITIVE LOGITS
     уз
    0.07
    invoices
    0.07
    薩
    0.06
     Rudd
    0.06
    起来
    0.06
    .redirect
    0.06
     nylon
    0.06
     고
    0.06
    .Public
    0.06
    ibilidad
    0.06
    Act Density 0.648%

    No Known Activations