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

    Neuronpedia

    INDEX
    Explanations

    really

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     houſe
    -1.07
     themſelves
    -1.06
     myſelf
    -1.05
     Majefty
    -1.02
     cauſe
    -0.97
     ſtate
    -0.96
     Reſ
    -0.94
     itſelf
    -0.93
     uſe
    -0.92
     Houſe
    -0.91
    POSITIVE LOGITS
    '
    0.61
     
    0.59
    ’
    0.57
    </table>
    0.56
    UnitTesting
    0.56
    ↵
    0.55
    </blockquote>
    0.54
     I
    0.52
    <eos>
    0.51
     M
    0.50
    Act Density 0.654%

    No Known Activations