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

    Neuronpedia

    INDEX
    Explanations

    toy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fulness
    -0.08
     огранич
    -0.06
     Parking
    -0.06
     Streams
    -0.06
     impecc
    -0.06
     대한
    -0.06
     Clin
    -0.06
     bridge
    -0.06
     sacr
    -0.06
     ком
    -0.06
    POSITIVE LOGITS
     Toys
    0.10
     toys
    0.09
     Toy
    0.08
    \core
    0.07
     фер
    0.07
    Toy
    0.07
    ("~/
    0.07
    豊
    0.07
     Dias
    0.06
    toi
    0.06
    Act Density 0.006%

    No Known Activations