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

    Neuronpedia

    INDEX
    Explanations

    error occurred during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Первая
    0.48
    цтва
    0.47
    褴
    0.46
     alarms
    0.43
     Эр
    0.42
     lục
    0.42
     disappears
    0.41
    otides
    0.41
     стре
    0.41
    ointees
    0.41
    POSITIVE LOGITS
    during
    0.55
     أثناء
    0.54
    ในการ
    0.52
    when
    0.52
     during
    0.52
     prilikom
    0.50
     durante
    0.47
     lors
    0.47
     beim
    0.46
    ्या
    0.46
    Act Density 0.029%

    No Known Activations