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

    Neuronpedia

    INDEX
    Explanations

    transition or continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ci
    0.54
    nti
    0.49
    nd
    0.47
    ati
    0.43
    的表现
    0.43
     общения
    0.43
    वेदनशील
    0.42
     निर्दिष्ट
    0.42
    anea
    0.42
    ukur
    0.41
    POSITIVE LOGITS
     ngunit
    0.52
    تالي
    0.48
    但
    0.48
     Paglin
    0.47
    ('-');
    0.47
    ною
    0.45
    サル
    0.45
    잘
    0.44
    ھار
    0.44
    ીર
    0.43
    Act Density 0.002%

    No Known Activations