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

    Neuronpedia

    INDEX
    Explanations

    mathematical pairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     measuring
    -0.08
    施工
    -0.08
     nozzle
    -0.08
    突出
    -0.07
     variability
    -0.07
     Schmerzen
    -0.07
    heus
    -0.07
     firing
    -0.07
     disappointing
    -0.07
     histó
    -0.07
    POSITIVE LOGITS
     pairs
    0.16
    Pairs
    0.16
    pairs
    0.15
    _pairs
    0.14
     parejas
    0.13
     paired
    0.12
     pairing
    0.12
    Pair
    0.12
    paired
    0.12
    (pair
    0.12
    Act Density 0.025%

    No Known Activations