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

    Neuronpedia

    INDEX
    Explanations

    word endings and stems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     horrend
    0.34
     PTSD
    0.34
     સંખ્યા
    0.33
     WebDriver
    0.32
     Decreto
    0.32
     Regex
    0.31
     cláus
    0.31
    🦵
    0.31
     aantal
    0.31
     🤗
    0.31
    POSITIVE LOGITS
    ↵
    0.50
    ي
    0.43
    the
    0.43
    u
    0.40
    The
    0.39
    و
    0.38
    '
    0.38
    i
    0.37
    ه
    0.35
    a
    0.35
    Act Density 0.610%

    No Known Activations