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

    Neuronpedia

    INDEX
    Explanations

    cleaning and tidiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ます
    1.27
    ますが
    1.22
    nél
    0.99
    么
    0.99
    tree
    0.99
    game
    0.97
    માં
    0.96
    smöglichkeiten
    0.96
    tile
    0.96
    tic
    0.94
    POSITIVE LOGITS
     sanitation
    1.18
     nanotubes
    1.15
    🧼
    1.13
     stains
    1.10
     disinfection
    1.08
     washing
    1.06
     commenc
    1.01
     Laund
    1.01
     cleans
    0.99
    liness
    0.97
    Act Density 0.050%

    No Known Activations