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

    Neuronpedia

    INDEX
    Explanations

    talking to the boss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     அறிந்த
    0.70
     स्टार्टअप
    0.59
    వృద్ధి
    0.58
     персонал
    0.58
    Просе
    0.56
    griffen
    0.56
     忄
    0.55
    дай
    0.54
     सशक्त
    0.54
     Mindfulness
    0.54
    POSITIVE LOGITS
    ↵↵
    0.67
    -
    0.67
     (
    0.51
    ier
    0.51
     boss
    0.50
    /
    0.49
    .
    0.47
    ).
    0.47
    ’
    0.46
    老板
    0.46
    Act Density 0.006%

    No Known Activations