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

    Neuronpedia

    INDEX
    Explanations

    code, filenames, and elements within code

    oai_token-act-pair · gemini-2.0-flash

    technical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -1.16
     (
    -1.05
      
    -0.98
     A
    -0.96
     I
    -0.95
     M
    -0.93
    ,
    -0.93
     C
    -0.93
     O
    -0.93
     "
    -0.91
    POSITIVE LOGITS
     Efq
    2.05
     myſelf
    2.00
     Theſe
    1.96
     Monfieur
    1.89
     itſelf
    1.85
     pleaſure
    1.80
     raiſ
    1.79
     ſeveral
    1.74
     Jefus
    1.73
     Majefty
    1.71
    Act Density 1.129%

    No Known Activations