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

    Neuronpedia

    INDEX
    Explanations

    international

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    辛勤
    -0.07
    フル
    -0.07
    ?=
    -0.07
    Translate
    -0.07
     хорош
    -0.07
    温馨
    -0.07
    ,args
    -0.07
    钰
    -0.07
     gravel
    -0.07
    新闻记者
    -0.07
    POSITIVE LOGITS
    kaza
    0.07
    contr
    0.07
    (container
    0.06
    带
    0.06
    	Vector
    0.06
    (instance
    0.06
    生产线
    0.06
     отно
    0.06
     primaryStage
    0.06
     oldu
    0.06
    Act Density 0.002%

    No Known Activations