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

    Neuronpedia

    INDEX
    Explanations

    Number of years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    913
    -0.07
    ご
    -0.07
    是
    -0.07
     是
    -0.07
    と
    -0.06
     závis
    -0.06
     gọi
    -0.06
    وری
    -0.06
     furious
    -0.06
    ]|
    -0.06
    POSITIVE LOGITS
     aberr
    0.07
    unter
    0.06
     Mitar
    0.06
    ’Brien
    0.06
    %);↵
    0.06
     GN
    0.06
    $↵
    0.06
     grabs
    0.06
    (expect
    0.06
     amidst
    0.06
    Act Density 0.050%

    No Known Activations