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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -good
    -0.08
    质量
    -0.07
     beide
    -0.07
     Desert
    -0.07
     Quint
    -0.06
     Depart
    -0.06
     Loch
    -0.06
    good
    -0.06
     coded
    -0.06
     Brno
    -0.06
    POSITIVE LOGITS
    ));↵↵↵
    0.07
    )++;↵
    0.07
    ='')↵
    0.07
    不到
    0.07
    áo
    0.07
     itk
    0.06
    /jav
    0.06
    		↵	↵
    0.06
    ("/")↵
    0.06
    :]↵↵
    0.06
    Act Density 0.016%

    No Known Activations