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

    Neuronpedia

    INDEX
    Explanations

    describing subsequent conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ల్ప
    0.47
     Ар
    0.46
    牖
    0.45
    炰
    0.43
    驽
    0.42
    綃
    0.42
    Ố
    0.42
     ವಿಧಾನ
    0.41
     до
    0.41
    нюю
    0.41
    POSITIVE LOGITS
    </h2>
    0.57
    an
    0.57
    ak
    0.57
    ai
    0.50
    io
    0.50
    zinho
    0.49
    weird
    0.49
    ig
    0.47
    aka
    0.46
    st
    0.46
    Act Density 0.000%

    No Known Activations