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

    Neuronpedia

    INDEX
    Explanations

    marx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fid
    -0.06
     Л
    -0.06
     нап
    -0.06
    logradouro
    -0.06
     пап
    -0.06
     bedding
    -0.06
     également
    -0.06
     pisc
    -0.06
     Finch
    -0.06
    .fast
    -0.06
    POSITIVE LOGITS
     Marx
    0.11
     Marxism
    0.08
     Marxist
    0.07
     activist
    0.07
     nghĩa
    0.06
    parameters
    0.06
    Updated
    0.06
     subsets
    0.06
     markup
    0.06
    RET
    0.06
    Act Density 0.003%

    No Known Activations