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

    Neuronpedia

    INDEX
    Explanations

    initial letters, often those of people's names, places, organizations or abbreviations

    oai_token-act-pair · gemini-2.0-flash

    Law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     B
    -2.56
     
    -2.56
     A
    -2.52
     M
    -2.52
     T
    -2.48
     R
    -2.47
     G
    -2.47
     P
    -2.45
     D
    -2.45
     S
    -2.41
    POSITIVE LOGITS
     myſelf
    4.66
     Monfieur
    4.66
     Anſ
    4.41
     itſelf
    4.38
     Reſ
    4.34
     Efq
    4.31
     Houſe
    4.31
     Theſe
    4.28
     Majefty
    4.25
     Diſ
    4.22
    Act Density 3.569%

    No Known Activations