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

    Neuronpedia

    INDEX
    Explanations

    dew drops and hope rebuild

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     제공
    0.53
    áva
    0.47
    を提供
    0.44
    提供
    0.41
    STON
    0.41
     permettant
    0.40
     предоставля
    0.40
     Doppel
    0.39
    提供了
    0.38
     अधिकांश
    0.38
    POSITIVE LOGITS
     بهذه
    0.43
     этими
    0.41
     brushed
    0.40
    他在
    0.40
     brush
    0.39
    これらの
    0.39
    рии
    0.38
    াগ
    0.38
     solchen
    0.38
     работу
    0.38
    Act Density 0.002%

    No Known Activations