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

    Neuronpedia

    INDEX
    Explanations

    structural elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Es
    -0.07
     easiest
    -0.06
     fields
    -0.06
     primitives
    -0.06
    apot
    -0.06
    Conversion
    -0.06
    طار
    -0.06
    oto
    -0.06
    Array
    -0.06
     diffusion
    -0.06
    POSITIVE LOGITS
    рис
    0.06
     ödem
    0.06
    677
    0.06
    .*?)
    0.06
    统计
    0.06
     EXPECT
    0.06
     Cena
    0.06
     पक
    0.06
    ився
    0.06
    loff
    0.06
    Act Density 0.072%

    No Known Activations