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

    Neuronpedia

    INDEX
    Explanations

    as many reps as possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ro
    0.45
     인
    0.40
     गिरी
    0.39
    LAGAB
    0.38
    鱷
    0.37
    ãng
    0.37
    Gab
    0.36
     Billboard
    0.36
    Firing
    0.35
     অভ্যন্ত
    0.35
    POSITIVE LOGITS
    飧
    0.39
    ate
    0.38
     расчет
    0.37
     Difer
    0.37
     രണ്ടു
    0.37
    {}'.
    0.36
     conjugate
    0.35
     čovjek
    0.35
     summing
    0.34
     contexts
    0.34
    Act Density 0.002%

    No Known Activations