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

    Neuronpedia

    INDEX
    Explanations

    low-hanging fruit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    좋
    0.47
     ноутбу
    0.44
    จึง
    0.43
     mathemat
    0.43
    䧺
    0.42
     zusätzlich
    0.41
    দৃশ্য
    0.41
    ంలో
    0.41
    ስታ
    0.41
     государственный
    0.40
    POSITIVE LOGITS
     जाति
    0.41
    限制
    0.38
     Fire
    0.38
     Eps
    0.36
    Fire
    0.35
     retrospect
    0.34
    rain
    0.34
     Infantry
    0.34
     Waring
    0.34
    شانی
    0.34
    Act Density 0.001%

    No Known Activations