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

    Neuronpedia

    INDEX
    Explanations

    Locke, Becker, H1B, write

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    op
    1.23
    v
    1.04
    s
    0.97
    THE
    0.96
    {
    0.95
    DO
    0.94
    }
    0.93
    /*
    0.92
    ```
    0.91
    }.
    0.91
    POSITIVE LOGITS
     사항
    1.28
    стью
    1.13
     сверху
    1.09
     spille
    1.09
     huống
    1.09
     åp
    1.06
     podrá
    1.05
     qualsiasi
    1.05
    নীয়
    1.05
     princípios
    1.04
    Act Density 0.003%

    No Known Activations