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

    Neuronpedia

    INDEX
    Explanations

    legal or official titles, activities, or categories

    oai_token-act-pair · gemini-2.0-flash

    civil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -0.76
     their
    -0.63
     so
    -0.61
     I
    -0.60
     or
    -0.59
     a
    -0.59
     much
    -0.56
     in
    -0.55
     his
    -0.55
     who
    -0.54
    POSITIVE LOGITS
     Jefus
    1.24
     itſelf
    1.20
     myſelf
    1.19
     Anſ
    1.13
     Efq
    1.13
     Mahomet
    1.09
     Cæsar
    1.06
     Monfieur
    1.06
     Shakspeare
    1.06
     Shaksp
    1.02
    Act Density 0.483%

    No Known Activations