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

    Neuronpedia

    INDEX
    Explanations

    array operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     welt
    -0.09
    -saving
    -0.09
    wekk
    -0.08
     lights
    -0.08
    打不开
    -0.08
     spinning
    -0.08
    .weather
    -0.08
     investments
    -0.08
     rents
    -0.08
     wards
    -0.08
    POSITIVE LOGITS
     duplicates
    0.12
    duplicates
    0.12
    _duplicates
    0.12
    Duplicates
    0.12
    .Unique
    0.11
    _unique
    0.10
    .unique
    0.10
    (predicate
    0.10
     membership
    0.10
    membership
    0.09
    Act Density 0.010%

    No Known Activations