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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.53
     itſelf
    -1.52
     myſelf
    -1.36
     Majefty
    -1.31
     becauſe
    -1.30
     Monfieur
    -1.30
     ſeveral
    -1.27
     Theſe
    -1.27
     Jefus
    -1.25
     houſe
    -1.23
    POSITIVE LOGITS
    '
    0.85
    ’
    0.85
     are
    0.77
     as
    0.73
     would
    0.71
     did
    0.71
     do
    0.70
     “
    0.70
     measure
    0.67
     (
    0.67
    Act Density 0.057%

    No Known Activations