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

    Neuronpedia

    INDEX
    Explanations

    nationalities/countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.59
     itſelf
    -1.57
     Cæsar
    -1.52
     Jefus
    -1.47
     Houſe
    -1.47
     Efq
    -1.47
     myſelf
    -1.47
     Majefty
    -1.46
     Anſ
    -1.44
     purpoſe
    -1.42
    POSITIVE LOGITS
     M
    0.81
     
    0.81
     “
    0.80
     I
    0.79
     "
    0.77
     U
    0.77
     can
    0.75
     T
    0.70
     ab
    0.70
     us
    0.70
    Act Density 0.063%

    No Known Activations