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

    Neuronpedia

    INDEX
    Explanations

    best or ultimate

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     基本
    0.42
     Overall
    0.41
    Overall
    0.41
     Themes
    0.40
    Icon
    0.39
    基本
    0.39
    Basic
    0.38
     compless
    0.37
    ICON
    0.36
     общего
    0.36
    POSITIVE LOGITS
     epitome
    0.86
     perfect
    0.78
     crux
    0.77
     proverbial
    0.73
     culmination
    0.71
     ultimate
    0.68
     ideal
    0.68
     holy
    0.66
     icing
    0.66
    perfect
    0.64
    Act Density 0.577%

    No Known Activations