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

    Neuronpedia

    INDEX
    Explanations

    how to connect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jedynie
    0.47
    昷
    0.43
     হয়ত
    0.42
    荭
    0.42
    밂
    0.42
    笄
    0.42
     plupart
    0.42
    胁
    0.41
     část
    0.41
    柠
    0.41
    POSITIVE LOGITS
    ？
    0.70
    ?
    0.63
    ？！
    0.53
    ?[
    0.50
    ?\
    0.50
    ?<
    0.49
    come
    0.47
    ?\\
    0.47
    ?>
    0.46
    ?!
    0.46
    Act Density 0.006%

    No Known Activations