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

    Neuronpedia

    INDEX
    Explanations

    Si

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ettings
    -0.07
     gem
    -0.07
    国家级
    -0.07
    Transformer
    -0.07
     của
    -0.07
    צי
    -0.07
    的意见
    -0.07
     consulting
    -0.06
     hut
    -0.06
    (filters
    -0.06
    POSITIVE LOGITS
    _TCP
    0.08
    /ap
    0.07
     *}↵↵
    0.07
     Multip
    0.06
    .bo
    0.06
     bề
    0.06
    訄
    0.06
    _hs
    0.06
    推理
    0.06
    afx
    0.06
    Act Density 0.001%

    No Known Activations