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

    Neuronpedia

    INDEX
    Explanations

    Code instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     atrak
    -0.08
    ,o
    -0.08
     selling
    -0.08
     aussi
    -0.08
     déta
    -0.08
     kyse
    -0.07
     incidence
    -0.07
    පා
    -0.07
     synthesized
    -0.07
     variations
    -0.07
    POSITIVE LOGITS
    ને
    0.08
    (".",
    0.08
    (".");↵
    0.08
    choose
    0.07
     ondernemen
    0.07
     Diario
    0.07
     dě
    0.07
     пользоваться
    0.07
    ("//
    0.07
     Woods
    0.07
    Act Density 0.004%

    No Known Activations