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

    Neuronpedia

    INDEX
    Explanations

    UK

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TRANSFER
    -0.08
    송
    -0.08
    ży
    -0.07
     Bun
    -0.07
     pare
    -0.07
    Se
    -0.07
     вар
    -0.07
     Const
    -0.07
    静
    -0.07
    =e
    -0.07
    POSITIVE LOGITS
     UK
    0.12
    UK
    0.09
     Kingdom
    0.08
     uk
    0.08
     EU
    0.07
    く
    0.07
    British
    0.07
    TableRow
    0.07
     regime
    0.07
    	Vk
    0.06
    Act Density 0.010%

    No Known Activations