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

    Neuronpedia

    INDEX
    Explanations

    lists, comparison, XOR, optionally create

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.87
    ल
    0.82
    s
    0.77
    d
    0.75
    лений
    0.72
    рист
    0.71
    t
    0.71
    0
    0.70
    स
    0.70
    د
    0.70
    POSITIVE LOGITS
    vadipine
    0.75
    ្សែ
    0.73
     उठाकर
    0.71
     dilwale
    0.70
    樎
    0.70
     Californie
    0.70
    ంక
    0.70
     avendo
    0.70
     الناتج
    0.69
    льнявыя
    0.69
    Act Density 0.001%

    No Known Activations