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

    Neuronpedia

    INDEX
    Explanations

    french history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —we
    -0.07
    (MSG
    -0.07
     años
    -0.07
    .region
    -0.07
    正
    -0.07
     marrying
    -0.07
     getPath
    -0.07
     forth
    -0.06
     PARAM
    -0.06
    \\"
    -0.06
    POSITIVE LOGITS
    дат
    0.08
     Motorola
    0.06
    ailer
    0.06
    pink
    0.06
    170
    0.05
    retim
    0.05
     станет
    0.05
     aspirations
    0.05
    牛
    0.05
    annah
    0.05
    Act Density 0.192%

    No Known Activations