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

    Neuronpedia

    INDEX
    Explanations

    An followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.60
    to
    0.49
    يك
    0.49
    </h5>
    0.47
    '},
    0.47
    😍
    0.47
    ف
    0.46
    ?}
    0.46
     अंदाज
    0.46
    </sub>
    0.46
    POSITIVE LOGITS
     an
    0.49
    ä
    0.47
     лекар
    0.45
    ність
    0.44
     évaluation
    0.43
    ong
    0.42
     экзем
    0.42
    з
    0.42
     extractive
    0.41
     eventuali
    0.41
    Act Density 0.655%

    No Known Activations