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

    Neuronpedia

    INDEX
    Explanations

    numbers and code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ellum
    0.68
     hitherto
    0.60
     মোটর
    0.60
     зависит
    0.57
     fémin
    0.56
     clim
    0.54
     deemed
    0.54
     等
    0.54
    ्यातील
    0.54
     childlike
    0.54
    POSITIVE LOGITS
     Tul
    0.59
     Momentum
    0.58
     गुल
    0.57
     tul
    0.56
     сад
    0.56
     OPTIONS
    0.54
     Kelly
    0.52
     XX
    0.51
     Marc
    0.50
     drop
    0.49
    Act Density 0.001%

    No Known Activations