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

    Neuronpedia

    INDEX
    Explanations

    code packages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Base
    -0.08
    	connection
    -0.07
    .Inv
    -0.07
     Castillo
    -0.07
     allergies
    -0.07
    	html
    -0.06
    	CHECK
    -0.06
     Kelly
    -0.06
     borrow
    -0.06
     Shoes
    -0.06
    POSITIVE LOGITS
    Tra
    0.07
    ẩy
    0.06
     выгляд
    0.06
     Spart
    0.06
     medio
    0.06
     Levitra
    0.06
     Thi
    0.06
     obchod
    0.06
     incorpor
    0.06
    �
    0.06
    Act Density 0.038%

    No Known Activations