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

    Neuronpedia

    INDEX
    Explanations

    Reagan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.52
     myſelf
    -1.48
     purpoſe
    -1.48
     Anſ
    -1.47
     Monfieur
    -1.46
     ſeveral
    -1.40
     reaſon
    -1.38
     ſtate
    -1.37
     itſelf
    -1.36
     Reſ
    -1.34
    POSITIVE LOGITS
     or
    0.87
     for
    0.84
     and
    0.84
     dem
    0.84
     (
    0.82
     b
    0.81
     vol
    0.81
     in
    0.80
     an
    0.80
     a
    0.80
    Act Density 0.071%

    No Known Activations