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

    Neuronpedia

    INDEX
    Explanations

    LaTeX math mode symbols

    oai_token-act-pair · gemini-2.0-flash

    Math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -
    -0.93
    ,
    -0.90
    .
    -0.80
     
    -0.72
    '
    -0.71
    !
    -0.70
    :
    -0.68
    ;
    -0.68
     (
    -0.67
    ...
    -0.67
    POSITIVE LOGITS
     itſelf
    1.45
     Monfieur
    1.40
     myſelf
    1.40
     Theſe
    1.38
     Efq
    1.32
     pleaſure
    1.28
     ſtate
    1.24
     auffi
    1.23
     Jefus
    1.23
     raiſ
    1.22
    Act Density 1.220%

    No Known Activations