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

    Neuronpedia

    INDEX
    Explanations

    why or do questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पश्चात
    0.39
     상
    0.38
    рованы
    0.38
     그죠
    0.37
     पुनः
    0.37
    శి
    0.37
    ScrollPane
    0.36
    renerg
    0.36
     anthocyan
    0.35
     이후
    0.35
    POSITIVE LOGITS
    ­
    0.55
    _
    0.49
     davvero
    0.46
    </h1>
    0.45
     surprisingly
    0.45
     ­
    0.43
    あなたの
    0.42
     واقعی
    0.39
    ’
    0.39
     ඔබේ
    0.38
    Act Density 0.017%

    No Known Activations