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

    Neuronpedia

    INDEX
    Explanations

    poverty and inequality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itchens
    -0.08
    есп
    -0.07
     verse
    -0.07
    РА
    -0.07
    """↵↵
    -0.07
     statutory
    -0.07
     Ingram
    -0.07
     duk
    -0.07
    .im
    -0.07
    check
    -0.07
    POSITIVE LOGITS
    NullOr
    0.08
    categorias
    0.06
    ForResult
    0.06
    IsNull
    0.06
     dış
    0.06
     notamment
    0.06
    .Angle
    0.06
     believable
    0.06
     україн
    0.06
     кредит
    0.05
    Act Density 0.106%

    No Known Activations