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

    Neuronpedia

    INDEX
    Explanations

    pay attention to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ណ៍
    0.76
     saturation
    0.70
     bread
    0.68
     birds
    0.66
     Birds
    0.66
     saturate
    0.64
    枋
    0.62
     Blink
    0.62
     kip
    0.60
     reprehenderit
    0.60
    POSITIVE LOGITS
     attention
    1.13
     atención
    0.94
    attention
    0.92
     Attention
    0.92
    Attention
    0.91
    PAL
    0.84
    stub
    0.82
    注意力
    0.82
    Stub
    0.82
    day
    0.82
    Act Density 0.115%

    No Known Activations