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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     census
    -0.07
     火
    -0.07
     pharmacy
    -0.07
     pais
    -0.06
     caus
    -0.06
     postcode
    -0.06
     sku
    -0.06
    IZATION
    -0.06
     colleg
    -0.06
     DOS
    -0.06
    POSITIVE LOGITS
    In
    0.10
     In
    0.09
    held
    0.07
     filament
    0.07
    iro
    0.06
     ultimately
    0.06
    อพ
    0.06
     royal
    0.06
     drift
    0.06
     الرمزية
    0.06
    Act Density 0.065%

    No Known Activations