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

    Neuronpedia

    INDEX
    Explanations

    for large

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ORDAN
    0.43
     څخه
    0.43
    に関する
    0.43
    Extension
    0.42
    TEMPLATE
    0.42
    ANDA
    0.41
    新たな
    0.41
    Ending
    0.41
    เพื่อให้
    0.41
    RELATES
    0.40
    POSITIVE LOGITS
     high
    0.63
     çoğu
    0.62
     large
    0.57
     plupart
    0.57
     novice
    0.57
     większość
    0.56
     normaal
    0.55
     wenn
    0.55
     basse
    0.55
    如果是
    0.53
    Act Density 0.023%

    No Known Activations