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

    Neuronpedia

    INDEX
    Explanations

    British things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     British
    -1.05
    British
    -0.91
     par
    -0.82
     of
    -0.71
     in
    -0.70
     a
    -0.70
     the
    -0.69
    british
    -0.68
     B
    -0.64
     and
    -0.63
    POSITIVE LOGITS
     purpoſe
    1.63
     Majefty
    1.61
     Efq
    1.55
     Houſe
    1.52
     itſelf
    1.51
     Anſ
    1.49
     myſelf
    1.48
     Monfieur
    1.45
     themſelves
    1.43
     ſever
    1.40
    Act Density 1.672%

    No Known Activations