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

    Neuronpedia

    INDEX
    Explanations

    text containing the word "respectively" and often relating to scientific study

    oai_token-act-pair · gemini-2.0-flash

    respectively

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     a
    -0.91
     the
    -0.79
     
    -0.77
     \
    -0.76
     P
    -0.75
      
    -0.74
     V
    -0.73
     In
    -0.72
     an
    -0.71
     (
    -0.71
    POSITIVE LOGITS
     myſelf
    1.34
     itſelf
    1.28
     auffi
    1.26
     Theſe
    1.23
    ſelf
    1.23
     pleaſure
    1.22
     Majefty
    1.21
     Monfieur
    1.20
     Efq
    1.20
     poffible
    1.20
    Act Density 1.769%

    No Known Activations