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

    Neuronpedia

    INDEX
    Explanations

    sustainability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tak
    -0.08
     Alley
    -0.07
     cellar
    -0.07
    λία
    -0.07
    学院
    -0.07
     bedrooms
    -0.06
     grated
    -0.06
    """)↵
    -0.06
     READ
    -0.06
    _room
    -0.06
    POSITIVE LOGITS
    _mov
    0.07
    ]={
    0.07
    uong
    0.06
    _tt
    0.06
     출연
    0.06
     kvin
    0.06
    ":[{"
    0.06
     newSize
    0.06
    のお
    0.06
     classic
    0.06
    Act Density 0.023%

    No Known Activations