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

    Neuronpedia

    INDEX
    Explanations

    French indefinite articles and related quantifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    French or German articles

    np_acts-logits-general · gemini-2.0-flash

    un certain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -1.01
     Majefty
    -1.00
     myſelf
    -0.97
     purpoſe
    -0.97
     Phry
    -0.95
     pleaſure
    -0.90
     beſt
    -0.89
     fubject
    -0.89
     Jefus
    -0.87
     himſelf
    -0.87
    POSITIVE LOGITS
     hundred
    0.81
     un
    0.79
     certain
    0.70
     Un
    0.67
     thousand
    0.66
     AssemblyTitle
    0.64
     „
    0.62
    -------------</
    0.62
     few
    0.61
     `
    0.61
    Act Density 0.018%

    No Known Activations