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

    Neuronpedia

    INDEX
    Explanations

    Party or House

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.77
     I
    -0.70
     C
    -0.67
     House
    -0.67
    ↵↵
    -0.64
     (
    -0.64
     K
    -0.64
     H
    -0.63
     G
    -0.63
     A
    -0.63
    POSITIVE LOGITS
     Efq
    1.70
     itſelf
    1.69
     myſelf
    1.61
     Anſ
    1.59
    ſelf
    1.58
     Reſ
    1.52
     Majefty
    1.52
    ſelves
    1.48
     faſt
    1.48
     Jefus
    1.47
    Act Density 2.588%

    No Known Activations