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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    1
    -0.79
    3
    -0.73
    2
    -0.69
    0
    -0.68
    6
    -0.68
    4
    -0.65
    8
    -0.64
    abestanden
    -0.60
    9
    -0.60
    7
    -0.60
    POSITIVE LOGITS
     للاسماء
    0.56
    原始内容存档于
    0.54
     five
    0.51
    Lähteet
    0.50
     NSObject
    0.48
    five
    0.48
    Carriera
    0.47
    jica
    0.47
    ValueStyle
    0.46
    Espèce
    0.46
    Act Density 0.008%

    No Known Activations