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

    Neuronpedia

    INDEX
    Explanations

    alias mirror and transmission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.61
    σης
    0.54
    ું
    0.54
    ста
    0.51
    are
    0.48
    helial
    0.48
    <0xBB>
    0.47
    <0xBC>
    0.47
    ходят
    0.47
    been
    0.47
    POSITIVE LOGITS
     frameworks
    0.52
     themes
    0.50
    စည်း
    0.50
    レビ
    0.50
     دینی
    0.49
     cubs
    0.49
    ๑
    0.49
    Events
    0.49
    年の
    0.48
     VMs
    0.48
    Act Density 0.001%

    No Known Activations