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

    Neuronpedia

    INDEX
    Explanations

    Instructions, requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .show
    -0.07
     結
    -0.07
        ↵↵↵
    -0.06
    لى
    -0.06
     Pittsburgh
    -0.06
     komb
    -0.06
    _MULTI
    -0.06
     मई
    -0.06
    ीध
    -0.06
     就
    -0.06
    POSITIVE LOGITS
     do
    0.10
     doing
    0.09
     done
    0.08
     DONE
    0.08
     Do
    0.08
     executed
    0.08
    Do
    0.07
    -done
    0.07
     imagem
    0.06
    Extent
    0.06
    Act Density 0.222%

    No Known Activations