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

    Neuronpedia

    INDEX
    Explanations

    legal and business language, especially surrounding patents and claims

    oai_token-act-pair · gemini-2.0-flash

    words related to combinations or arrangements

    np_token-act-pair-logits · gpt-4o-mini

    Legal texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     épaules
    -0.81
     lèvres
    -0.73
     enfans
    -0.72
     genoux
    -0.72
     marquées
    -0.72
     célèbres
    -0.70
     vägen
    -0.70
     barnen
    -0.70
     dieux
    -0.69
     connus
    -0.69
    POSITIVE LOGITS
     arrangement
    0.84
     background
    0.79
     mixture
    0.79
    })*/
    0.77
    #+#
    0.77
     solution
    0.77
     division
    0.76
    ")){
    0.75
     combination
    0.74
     information
    0.74
    Act Density 12.549%

    No Known Activations