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

    Neuronpedia

    INDEX
    Explanations

    cautious about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    های
    0.57
    ًا
    0.50
     நகர
    0.50
    ные
    0.50
    のために
    0.48
    ко
    0.47
    ві
    0.47
     многочис
    0.46
    는
    0.45
    trimethyl
    0.45
    POSITIVE LOGITS
     about
    0.54
     accessibility
    0.52
     अबाउट
    0.50
     discrepancies
    0.50
     tentang
    0.50
     authorizing
    0.49
     disparities
    0.48
     monies
    0.47
     productivity
    0.46
    ھار
    0.46
    Act Density 0.002%

    No Known Activations