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

    Neuronpedia

    INDEX
    Explanations

    defense and strongholds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.60
     Monfieur
    -1.59
     Jefus
    -1.45
     Efq
    -1.42
     Houſe
    -1.40
     Majefty
    -1.39
     itſelf
    -1.38
     Chriftian
    -1.38
     himſelf
    -1.32
     houſe
    -1.31
    POSITIVE LOGITS
    a
    1.12
    ed
    1.04
    e
    1.00
    i
    0.99
    ly
    0.81
    o
    0.78
     ri
    0.71
    en
    0.69
     gra
    0.69
    edin
    0.68
    Act Density 0.046%

    No Known Activations