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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manages
    -0.07
     shiny
    -0.07
    ,a
    -0.07
     kinda
    -0.07
     dressed
    -0.07
    Strings
    -0.06
    (pref
    -0.06
    Emergency
    -0.06
     gl
    -0.06
    ，这
    -0.06
    POSITIVE LOGITS
    ChartData
    0.07
    tridge
    0.06
     lý
    0.06
    ビ
    0.06
    ́t
    0.06
    yle
    0.06
    ικο
    0.06
    cessive
    0.06
    _>
    0.06
     toy
    0.06
    Act Density 0.002%

    No Known Activations