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

    Neuronpedia

    INDEX
    Explanations

    built on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    女友
    0.54
    㳓
    0.51
     genotyping
    0.48
    ayvachi
    0.48
    лефон
    0.47
    ത്തിനു
    0.46
     구입
    0.45
     ಅಧಿಕಾರಿ
    0.45
     adhipp
    0.45
    䊂
    0.45
    POSITIVE LOGITS
     G
    0.43
    exception
    0.41
     W
    0.41
     P
    0.41
     C
    0.40
    e
    0.40
     R
    0.40
    ↵
    0.39
      
    0.39
     de
    0.39
    Act Density 0.002%

    No Known Activations