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

    Neuronpedia

    INDEX
    Explanations

    continuity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.14
     ſever
    -1.05
     Efq
    -1.03
     Majefty
    -0.94
     themſelves
    -0.93
    出版年
    -0.93
     myſelf
    -0.93
     itſelf
    -0.90
     Houſe
    -0.89
     houſe
    -0.88
    POSITIVE LOGITS
     زاده
    0.57
     to
    0.56
     de
    0.54
     (
    0.53
     for
    0.52
     or
    0.51
     of
    0.51
     “
    0.51
    ,
    0.51
    <eos>
    0.49
    Act Density 1.348%

    No Known Activations