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

    Neuronpedia

    INDEX
    Explanations

    Health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Combine
    -0.06
    alace
    -0.06
     внутріш
    -0.06
     �
    -0.06
    pects
    -0.06
    OO
    -0.06
    ardash
    -0.06
     Sat
    -0.06
     комму
    -0.06
    _az
    -0.06
    POSITIVE LOGITS
    人们
    0.07
    EndDate
    0.06
     occupational
    0.06
     consequently
    0.06
     Foster
    0.06
     diabetes
    0.06
    ическим
    0.06
    �
    0.06
     Card
    0.06
    /types
    0.06
    Act Density 0.000%

    No Known Activations