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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Geile
    -0.07
    ████
    -0.06
    -Shirt
    -0.06
    tolower
    -0.06
     Siz
    -0.06
     ΠΡ
    -0.06
    督
    -0.06
     Spotlight
    -0.06
     mistakenly
    -0.06
     poste
    -0.06
    POSITIVE LOGITS
    件
    0.07
     gauge
    0.06
     merging
    0.06
     выполн
    0.06
    [method
    0.06
    Positions
    0.06
    #endregion
    0.06
     Друг
    0.06
     almond
    0.06
    olicy
    0.06
    Act Density 0.054%

    No Known Activations