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

    Neuronpedia

    INDEX
    Explanations

    package information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    于是
    0.40
    foregroundView
    0.39
     emir
    0.38
     زا
    0.38
     Cavendish
    0.38
    цов
    0.37
    فات
    0.37
     Qatar
    0.37
    循环
    0.37
     едино
    0.37
    POSITIVE LOGITS
    "};
    0.41
     কর্তৃক
    0.37
    支払い
    0.37
    ###########
    0.36
    KB
    0.36
    #########
    0.36
    auts
    0.35
    indir
    0.35
     Gets
    0.35
    erals
    0.35
    Act Density 0.000%

    No Known Activations