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

    Neuronpedia

    INDEX
    Explanations

    attention and focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wing
    0.84
    ∨
    0.67
     سبق
    0.62
     सुर
    0.61
     यूज
    0.61
    ገድ
    0.60
    ካ
    0.60
     nameof
    0.60
     Phát
    0.59
    ovia
    0.59
    POSITIVE LOGITS
     attention
    4.48
     Attention
    3.92
    attention
    3.82
    Attention
    3.71
     atenção
    3.44
     внимание
    3.44
     attentions
    3.39
    attenzione
    3.37
     attenzione
    3.26
     внимания
    3.25
    Act Density 0.269%

    No Known Activations