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

    Neuronpedia

    INDEX
    Explanations

    dynamic content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     benöt
    0.42
    เรา
    0.41
    *=
    0.41
     বোপ
    0.40
     हमको
    0.40
     우리는
    0.39
    ैट
    0.39
     ወደ
    0.38
    для
    0.38
     ڤ
    0.38
    POSITIVE LOGITS
    dynamic
    0.51
     dynamism
    0.51
     personal
    0.50
     динами
    0.50
     dynamic
    0.49
     employee
    0.48
    personal
    0.48
     Chairman
    0.46
     its
    0.46
    customer
    0.46
    Act Density 0.003%

    No Known Activations