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

    Neuronpedia

    INDEX
    Explanations

    packages and delivery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.52
    ř
    0.50
     mangroves
    0.49
     Tonga
    0.49
    2
    0.47
    DF
    0.46
     ocasião
    0.46
    mère
    0.46
    ny
    0.45
    for
    0.45
    POSITIVE LOGITS
    пион
    0.42
    ιος
    0.42
    したが
    0.42
     কিং
    0.41
     उतना
    0.40
     সম্পাদক
    0.40
    يارات
    0.40
    зация
    0.40
    ပ်
    0.39
     приме
    0.39
    Act Density 0.000%

    No Known Activations