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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     that
    -1.02
    ,
    -0.89
     a
    -0.83
     
    -0.83
     an
    -0.77
     (
    -0.77
    :
    -0.77
    .
    -0.71
    (
    -0.68
     on
    -0.68
    POSITIVE LOGITS
     myſelf
    1.23
     Efq
    1.16
     purpoſe
    1.06
     Theſe
    1.04
     faſt
    1.03
     itſelf
    1.00
    AddTagHelper
    0.97
     Anſ
    0.95
     Monfieur
    0.95
     pleaſure
    0.93
    Act Density 0.327%

    No Known Activations