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

    Neuronpedia

    INDEX
    Explanations

    Python imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theirs
    0.91
    時には
    0.79
     നിന്ന്
    0.75
    WQ
    0.73
    让他们
    0.72
     retiro
    0.72
     Their
    0.71
     loro
    0.71
    ੋਂ
    0.70
     appré
    0.70
    POSITIVE LOGITS
    ...........
    0.94
    ......
    0.92
    .....
    0.89
    ..........
    0.89
    .......
    0.88
    .........
    0.85
    ............
    0.84
    ........
    0.82
    ..............
    0.81
    。。。
    0.78
    Act Density 0.000%

    No Known Activations