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

    Neuronpedia

    INDEX
    Explanations

    numbers and divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    য়
    0.39
     তীরে
    0.38
     ওখানে
    0.38
     سائٹ
    0.37
     写
    0.35
     зру
    0.35
    寫
    0.34
    USTR
    0.34
     infinitely
    0.33
    的效果
    0.33
    POSITIVE LOGITS
    mostly
    0.47
     liczba
    0.47
    കു
    0.46
     मल्टी
    0.45
    rare
    0.45
     संख्या
    0.45
    raham
    0.45
     insignia
    0.44
    数目
    0.44
    햐
    0.44
    Act Density 0.004%

    No Known Activations