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

    Neuronpedia

    INDEX
    Explanations

    named entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shakspeare
    -1.82
     itſelf
    -1.55
     myſelf
    -1.54
     Cæsar
    -1.51
     Shaksp
    -1.51
     Jefus
    -1.44
     Efq
    -1.41
     Monfieur
    -1.39
     Charlemagne
    -1.32
     houſe
    -1.27
    POSITIVE LOGITS
     
    0.84
    '
    0.80
    ’
    0.79
    an
    0.77
     The
    0.75
     I
    0.68
     A
    0.67
     (
    0.65
     in
    0.64
     "
    0.64
    Act Density 0.136%

    No Known Activations