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

    Neuronpedia

    INDEX
    Explanations

    research projects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ⰽ
    -0.08
    打得
    -0.07
     Neville
    -0.07
    英文
    -0.07
    쓺
    -0.07
    泄漏
    -0.07
     informs
    -0.07
    但也
    -0.07
    ﭩ
    -0.06
     Phương
    -0.06
    POSITIVE LOGITS
    ET
    0.08
     выбира
    0.08
    _top
    0.07
     próximo
    0.07
    parator
    0.07
     pipelines
    0.07
    SearchTree
    0.07
     Sem
    0.07
    ,\
    0.07
    Tester
    0.07
    Act Density 0.052%

    No Known Activations