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

    Neuronpedia

    INDEX
    Explanations

    AI, Lua Script, three legs, steel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    空気
    0.40
    PGS
    0.39
    edom
    0.39
     পাদ
    0.39
    tabPage
    0.38
    isas
    0.38
    endaft
    0.38
     ZH
    0.38
    Alex
    0.38
    Mileage
    0.37
    POSITIVE LOGITS
     unkind
    0.40
     unlikely
    0.40
     sty
    0.40
     trapping
    0.39
     needy
    0.39
     thumbnail
    0.39
     robbing
    0.39
     मेटा
    0.38
     signific
    0.38
     algebraic
    0.38
    Act Density 0.001%

    No Known Activations