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

    Neuronpedia

    INDEX
    Explanations

    references to sports statistics, teams, and wins

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :✨
    -0.91
     Monfieur
    -0.87
     houſe
    -0.76
     ſtate
    -0.75
     Diſ
    -0.75
     Houſe
    -0.71
     Majefty
    -0.71
     myſelf
    -0.71
     Efq
    -0.70
     ſta
    -0.70
    POSITIVE LOGITS
    ,
    0.52
    .
    0.47
    mbggenerated
    0.47
    -
    0.47
     A
    0.46
     --
    0.45
    —
    0.44
     g
    0.41
    ...
    0.40
     —
    0.40
    Act Density 5.221%

    No Known Activations