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

    Neuronpedia

    INDEX
    Explanations

    gladness to you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h1>
    0.52
    When
    0.50
    when
    0.50
    this
    0.48
    इस
    0.48
     ล
    0.47
    ဤ
    0.46
    <>
    0.44
    Voor
    0.44
     дли
    0.44
    POSITIVE LOGITS
     to
    0.64
     you
    0.58
     glad
    0.51
     confirme
    0.51
     видеть
    0.49
     finally
    0.48
    ار
    0.47
     Glad
    0.46
     confirmar
    0.46
     confirm
    0.46
    Act Density 0.027%

    No Known Activations