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

    Neuronpedia

    INDEX
    Explanations

    ellipses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :s
    -0.07
     whiskey
    -0.07
     respectively
    -0.06
    Median
    -0.06
    уются
    -0.06
    ोम
    -0.06
     ``(
    -0.06
    =output
    -0.06
    cou
    -0.06
    iate
    -0.06
    POSITIVE LOGITS
    .httpClient
    0.06
    乎
    0.06
    .Menu
    0.06
    aeda
    0.06
    FunctionFlags
    0.06
     зовніш
    0.06
    .warn
    0.06
     Produ
    0.06
    áj
    0.06
     речі
    0.06
    Act Density 0.009%

    No Known Activations