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

    Neuronpedia

    INDEX
    Explanations

    Actions/Events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.42
     Diſ
    -1.35
     Monfieur
    -1.35
     Theſe
    -1.34
     itſelf
    -1.31
     Anſ
    -1.30
     Jefus
    -1.28
     Reſ
    -1.27
     Majefty
    -1.27
    ſelf
    -1.24
    POSITIVE LOGITS
     of
    0.81
     in
    0.68
     a
    0.66
     the
    0.65
     can
    0.60
     (
    0.57
     la
    0.57
     I
    0.57
     He
    0.57
     he
    0.56
    Act Density 1.597%

    No Known Activations