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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Louis
    0.93
    Louis
    0.89
    /,
    0.88
     LOUIS
    0.87
     Perrin
    0.87
    Lou
    0.81
     Rous
    0.80
     naf
    0.79
     louis
    0.77
     Lou
    0.76
    POSITIVE LOGITS
    }//
    1.62
    };//
    1.28
    ++;//
    1.26
    ));//
    1.25
    ";//
    1.21
     }//
    1.20
    ");//
    1.19
    ){//
    1.17
    ');//
    1.14
    );//
    1.14
    Act Density 0.031%

    No Known Activations