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

    Neuronpedia

    INDEX
    Explanations

    royal titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     king
    -1.73
     King
    -1.67
    King
    -1.56
     KING
    -1.55
     queen
    -1.43
     kings
    -1.42
     QUEEN
    -1.36
     Queen
    -1.34
    Queen
    -1.23
    queen
    -1.15
    POSITIVE LOGITS
     Fragment
    0.48
     BorderRadius
    0.45
    Fragment
    0.44
     Ga
    0.44
     Release
    0.44
    '
    0.44
     Ex
    0.43
    Les
    0.43
     Vault
    0.43
     Les
    0.43
    Act Density 0.102%

    No Known Activations