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

    Neuronpedia

    INDEX
    Explanations

    UK emergency contact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🎃
    0.42
    en
    0.41
    時期
    0.41
    报错
    0.41
    ‌
    0.41
    ⤦
    0.41
     Firstly
    0.40
    🍂
    0.40
    Montserrat
    0.40
    <strong>
    0.39
    POSITIVE LOGITS
     ඔවුන්
    0.51
     их
    0.50
    стом
    0.49
     декла
    0.48
     njihov
    0.48
    谀
    0.48
     তারাও
    0.48
     quotas
    0.46
    මාන්
    0.46
    ین
    0.46
    Act Density 0.008%

    No Known Activations