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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    พย
    -0.07
    oris
    -0.07
    .product
    -0.06
    $menu
    -0.06
    .fp
    -0.06
     витами
    -0.06
    -my
    -0.06
     hatta
    -0.06
     telephone
    -0.06
     tokenize
    -0.06
    POSITIVE LOGITS
     Attribute
    0.08
     Recall
    0.08
     dwar
    0.07
     agora
    0.07
    ...',
    0.07
     dém
    0.06
    σταση
    0.06
    ("--------------------------------
    0.06
     --------------------------------
    0.06
     ************************
    0.06
    Act Density 0.012%

    No Known Activations