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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dart
    -0.06
     David
    -0.06
     field
    -0.06
    cassert
    -0.06
     backyard
    -0.06
     top
    -0.06
     td
    -0.06
     benefited
    -0.06
     measured
    -0.06
    trade
    -0.06
    POSITIVE LOGITS
     ones
    0.10
    ун
    0.08
     المتحدة
    0.08
    UN
    0.08
     Nations
    0.08
    ernals
    0.07
    one
    0.07
     Ones
    0.07
     Onc
    0.07
     ين
    0.07
    Act Density 0.032%

    No Known Activations