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

    Neuronpedia

    INDEX
    Explanations

    serve as or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sympt
    0.39
     Oste
    0.37
     Alles
    0.36
     œuvres
    0.36
     EN
    0.36
     Prices
    0.36
     Fees
    0.36
    嶙
    0.36
     ys
    0.35
     Éireann
    0.35
    POSITIVE LOGITS
     served
    0.89
     serve
    0.88
    Serve
    0.84
     serves
    0.83
     serving
    0.76
    served
    0.73
     Served
    0.70
    serve
    0.70
     Serve
    0.69
    Served
    0.66
    Act Density 0.007%

    No Known Activations