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

    Neuronpedia

    INDEX
    Explanations

    indented lines

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
      
    -0.82
    ,
    -0.77
     (
    -0.73
     -
    -0.70
     “
    -0.69
     or
    -0.67
    ...
    -0.67
     T
    -0.66
     –
    -0.65
    /
    -0.64
    POSITIVE LOGITS
     Efq
    1.57
     Majefty
    1.48
     myſelf
    1.41
     Anſ
    1.36
     itſelf
    1.32
     Jefus
    1.31
     Theſe
    1.30
     Reſ
    1.28
     Monfieur
    1.27
     ſeveral
    1.25
    Act Density 0.007%

    No Known Activations