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

    Neuronpedia

    INDEX
    Explanations

    Iberian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.34
     purpoſe
    -1.29
     Majefty
    -1.23
     itſelf
    -1.21
     raiſ
    -1.20
     Efq
    -1.20
     himſelf
    -1.19
     Diſ
    -1.19
     ſtate
    -1.18
     houſe
    -1.18
    POSITIVE LOGITS
    LabelTagHelper
    0.46
    on
    0.45
    M
    0.43
    umont
    0.43
     Of
    0.42
     supérieures
    0.42
    ly
    0.41
    s
    0.41
    '
    0.41
     Which
    0.41
    Act Density 0.048%

    No Known Activations