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

    Neuronpedia

    INDEX
    Explanations

    words that express positive sentiment or are related to embellishment/decoration

    oai_token-act-pair · gemini-2.0-flash

    fancy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.95
    <eos>
    -0.89
     on
    -0.87
    ,
    -0.84
     a
    -0.84
     in
    -0.83
     M
    -0.83
     I
    -0.83
     P
    -0.82
     K
    -0.79
    POSITIVE LOGITS
     myſelf
    1.91
     itſelf
    1.87
     Monfieur
    1.84
     Theſe
    1.77
     pleaſure
    1.75
     Anſ
    1.74
     Majefty
    1.74
     Jefus
    1.74
     purpoſe
    1.73
     ་་
    1.66
    Act Density 1.806%

    No Known Activations