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

    Neuronpedia

    INDEX
    Explanations

    directional words such as left and right

    oai_token-act-pair · gemini-2.0-flash

    left right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expandindo
    -0.66
    LookAnd
    -0.60
    жели
    -0.52
    abstractmethod
    -0.51
    Datuak
    -0.51
     CURIAM
    -0.50
     internetowa
    -0.50
    UnitTesting
    -0.49
     nonUne
    -0.49
    SBATCH
    -0.48
    POSITIVE LOGITS
     Left
    1.01
     left
    0.96
    Left
    0.91
     LEFT
    0.91
    LEFT
    0.87
    left
    0.82
     sinistra
    0.82
     Right
    0.76
     左
    0.75
    Right
    0.74
    Act Density 1.012%

    No Known Activations