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

    Neuronpedia

    INDEX
    Explanations

    strings of dashes and the suffix "lia."

    oai_token-act-pair · gemini-2.0-flash

    –

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -2.64
     itſelf
    -2.52
     Efq
    -2.36
     Monfieur
    -2.30
     pleaſure
    -2.17
     purpoſe
    -2.17
     Jefus
    -2.17
     ſeveral
    -2.16
     himſelf
    -2.06
     Theſe
    -2.06
    POSITIVE LOGITS
    ,
    1.48
    .
    1.43
     
    1.34
    '
    1.28
    ;
    1.24
    <eos>
    1.23
    :
    1.22
     in
    1.20
    ?
    1.19
    /
    1.17
    Act Density 7.162%

    No Known Activations