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

    Neuronpedia

    INDEX
    Explanations

    creating and building

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Newly
    0.82
     Recent
    0.72
     recién
    0.68
     Recently
    0.68
     Established
    0.66
     최근
    0.66
    RECENT
    0.65
    Newly
    0.65
    Recent
    0.64
     Upcoming
    0.64
    POSITIVE LOGITS
     effective
    0.91
     custom
    0.88
     efficient
    0.88
     customized
    0.87
     bespoke
    0.86
     workable
    0.84
     believable
    0.82
     personalized
    0.82
     coherent
    0.81
     lasting
    0.78
    Act Density 0.909%

    No Known Activations