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

    Neuronpedia

    INDEX
    Explanations

    analysis and expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étaient
    0.39
     jsou
    0.36
     tohoto
    0.35
     THIS
    0.33
     této
    0.32
     تھے
    0.32
     estão
    0.32
     هذا
    0.32
     janë
    0.32
     están
    0.32
    POSITIVE LOGITS
    更容易
    0.47
     путем
    0.46
    从而
    0.45
     poprzez
    0.44
     உதவுக
    0.44
     while
    0.43
     وبالتالي
    0.43
    而
    0.43
     Allows
    0.43
     Thereby
    0.42
    Act Density 0.409%

    No Known Activations