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

    Neuronpedia

    INDEX
    Explanations

    Spain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spain
    -1.19
     Spaniards
    -1.13
     Efq
    -1.13
     Spanish
    -1.10
     Spaniard
    -1.05
     Spanien
    -1.03
     SPANISH
    -1.03
     Theſe
    -1.03
     spanish
    -1.02
     Anſ
    -1.02
    POSITIVE LOGITS
    '
    0.54
     P
    0.53
     
    0.53
    .
    0.53
    P
    0.49
    ’
    0.49
     Bel
    0.48
    val
    0.48
    vo
    0.48
     c
    0.47
    Act Density 0.452%

    No Known Activations