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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Person
    -0.07
    .reducer
    -0.06
    运行
    -0.06
    	random
    -0.06
     NDEBUG
    -0.06
    isi
    -0.06
    _yellow
    -0.06
     IPs
    -0.06
    软
    -0.06
     cca
    -0.06
    POSITIVE LOGITS
    ブラ
    0.07
     parte
    0.06
    SITE
    0.06
     CONTR
    0.06
     incumb
    0.06
     con
    0.06
     Fully
    0.06
     mamma
    0.06
     urge
    0.06
    .BooleanField
    0.06
    Act Density 0.001%

    No Known Activations