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

    Neuronpedia

    INDEX
    Explanations

    ya

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     you
    -1.45
     Monfieur
    -1.23
     itſelf
    -1.14
     Efq
    -1.04
     myſelf
    -1.04
     pleaſure
    -1.03
     ſeveral
    -1.02
     poffible
    -1.02
     Jefus
    -1.00
     fevere
    -0.98
    POSITIVE LOGITS
     are
    0.90
    ’
    0.89
     can
    0.84
     were
    0.77
    '
    0.70
     and
    0.65
     will
    0.62
     may
    0.61
    ,
    0.59
     have
    0.58
    Act Density 1.620%

    No Known Activations