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

    Neuronpedia

    INDEX
    Explanations

    attention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attention
    -1.60
    Attention
    -1.43
    attention
    -1.42
     Attention
    -1.40
     ATTENTION
    -1.28
     atenção
    -1.18
     attenzione
    -1.07
     atención
    -1.04
    ATTENTION
    -1.03
     внимание
    -0.99
    POSITIVE LOGITS
     the
    0.65
    al
    0.59
    DataPropertyName
    0.56
    ary
    0.55
    viewDidLoad
    0.54
    e
    0.54
    kian
    0.53
    nten
    0.52
    k
    0.52
    ful
    0.52
    Act Density 1.372%

    No Known Activations