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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.81
     I
    -0.75
     “
    -0.71
     (
    -0.68
     "
    -0.66
     P
    -0.65
     ‘
    -0.65
     all
    -0.63
     as
    -0.63
     but
    -0.63
    POSITIVE LOGITS
     Efq
    1.81
     Monfieur
    1.62
     Majefty
    1.61
     myſelf
    1.59
     Jefus
    1.56
     itſelf
    1.56
     Reſ
    1.52
     Chriftian
    1.48
     Houſe
    1.45
     Diſ
    1.44
    Act Density 0.043%

    No Known Activations