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

    Neuronpedia

    INDEX
    Explanations

    fluoride

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ी
    2.68
    я
    2.43
    া
    2.28
    ्यां
    2.27
    ि
    2.27
    েরও
    2.27
    ும்
    2.23
    aib
    2.15
    در
    2.13
    ास
    2.11
    POSITIVE LOGITS
    ক্রিয়
    2.13
    িত
    2.12
    ून
    2.10
    manship
    2.07
    涑
    2.06
    ございます
    2.04
    こちらの
    2.00
    ರ
    1.99
    ਾਰ
    1.95
    完毕
    1.92
    Act Density 0.004%

    No Known Activations