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

    Neuronpedia

    INDEX
    Explanations

    continuously improve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ouais
    0.47
     მიმოწერა
    0.46
    民國
    0.45
     Estadual
    0.44
     হত্যাকাণ্ড
    0.44
    ceğim
    0.44
     Балтбет
    0.44
    চ্ছ
    0.43
    avid
    0.43
    чната
    0.43
    POSITIVE LOGITS
    লিন
    0.51
     income
    0.48
     obj
    0.47
     liners
    0.47
     analysis
    0.46
     অভিজ্ঞ
    0.45
     experi
    0.44
     enabling
    0.44
     additive
    0.44
    n
    0.44
    Act Density 0.003%

    No Known Activations