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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     end
    -1.88
     rest
    -1.15
     art
    -1.15
     
    -1.15
     des
    -1.08
     est
    -1.05
     de
    -1.03
     (
    -1.02
     in
    -0.98
     E
    -0.97
    POSITIVE LOGITS
     Efq
    2.48
     myſelf
    2.39
     itſelf
    2.34
     Monfieur
    2.33
     houſe
    2.23
     Houſe
    2.23
     Theſe
    2.22
     purpoſe
    2.20
     pleaſure
    2.16
     ſeveral
    2.13
    Act Density 0.149%

    No Known Activations