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

    Neuronpedia

    INDEX
    Explanations

    how to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     juicy
    0.98
     if
    0.84
     orice
    0.83
     lips
    0.82
    하
    0.82
    이나
    0.81
    涷
    0.80
     and
    0.80
    Depois
    0.80
    ुर
    0.79
    POSITIVE LOGITS
    ו
    0.87
    strategy
    0.86
    و
    0.86
     ۴
    0.85
    க்கம்
    0.80
    intégration
    0.80
    e
    0.80
    segment
    0.79
    ++.
    0.79
    revenue
    0.79
    Act Density 0.001%

    No Known Activations