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

    Neuronpedia

    INDEX
    Explanations

    cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.78
     Jan
    -0.75
     Cor
    -0.73
     J
    -0.67
     the
    -0.66
     last
    -0.65
     Fried
    -0.62
     Gu
    -0.62
     par
    -0.61
     March
    -0.60
    POSITIVE LOGITS
     Efq
    1.47
     myſelf
    1.34
     Monfieur
    1.34
     houſe
    1.32
     Houſe
    1.32
     Jefus
    1.31
     Theſe
    1.30
     Diſ
    1.26
     raiſ
    1.26
     Majefty
    1.26
    Act Density 1.737%

    No Known Activations