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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lékař
    -0.07
     Bast
    -0.06
     Yatırım
    -0.06
     genocide
    -0.06
    GetName
    -0.06
     Generate
    -0.06
     mq
    -0.06
     Roz
    -0.06
     //----------------------------------------------------------------
    -0.06
     Woo
    -0.05
    POSITIVE LOGITS
    express
    0.08
    偶
    0.07
     insets
    0.07
    -eye
    0.07
    жно
    0.06
     hemp
    0.06
    (png
    0.06
    (ws
    0.06
    еств
    0.06
     desc
    0.06
    Act Density 0.019%

    No Known Activations