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

    Neuronpedia

    INDEX
    Explanations

    references to figures and tables in research papers

    oai_token-act-pair · gemini-2.0-flash

    figure/table references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.48
     L
    -0.47
    絮
    -0.46
     #
    -0.44
     Lang
    -0.43
    righ
    -0.43
    umi
    -0.43
    ########.
    -0.41
     vào
    -0.40
    </tbody>
    -0.40
    POSITIVE LOGITS
     Efq
    0.94
     pleaſure
    0.93
     myſelf
    0.92
     Theſe
    0.85
     Diſ
    0.84
    )";
    0.84
     houſe
    0.84
     itſelf
    0.84
     Cæsar
    0.82
     ſche
    0.82
    Act Density 0.584%

    No Known Activations