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

    Neuronpedia

    INDEX
    Explanations

    the substrings "ter", "Bur", or "v" in what seems to be code or legal text

    oai_token-act-pair · gemini-2.0-flash

    ter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -
    -1.38
    ↵↵
    -1.21
    ↵
    -1.15
    ,
    -1.15
     of
    -1.11
    /
    -1.08
     (
    -1.04
     
    -1.03
    .
    -1.00
     and
    -0.99
    POSITIVE LOGITS
     Efq
    2.22
     Monfieur
    2.17
     ainfi
    2.13
     myſelf
    2.05
     purpoſe
    1.91
     Jefus
    1.91
     Theſe
    1.90
     ſeveral
    1.89
     feroit
    1.87
     للاسماء
    1.87
    Act Density 3.258%

    No Known Activations