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

    Neuronpedia

    INDEX
    Explanations

    stability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Pointer
    -0.06
     repr
    -0.06
    Sur
    -0.06
     consum
    -0.06
     Aus
    -0.06
    .AddScoped
    -0.06
     ----------------------------------------------------------------------------
    -0.06
    Dictionary
    -0.06
     lety
    -0.05
    (Parameter
    -0.05
    POSITIVE LOGITS
    вая
    0.07
     squares
    0.07
    .toJson
    0.07
     biết
    0.07
    .text
    0.06
    起来
    0.06
    	Json
    0.06
     clic
    0.06
     件
    0.06
     Bai
    0.06
    Act Density 0.007%

    No Known Activations