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

    Neuronpedia

    INDEX
    Explanations

    descriptive language related to architecture and design

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

    preceding description words like "design", "menu", and "bouquet"

    np_acts-logits-general · gemini-2.0-flash

    describes showcases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.59
    ValueStyle
    -0.58
     supplementary
    -0.56
    ISupport
    -0.56
     appendices
    -0.54
     ſtre
    -0.54
     ſta
    -0.53
    OrNil
    -0.53
    PreExecute
    -0.53
     horrible
    -0.53
    POSITIVE LOGITS
     ex
    1.11
     Paying
    0.83
     paying
    0.83
     evoke
    0.77
     pays
    0.76
     showcases
    0.76
     evokes
    0.75
    Paying
    0.75
     pay
    0.74
     hark
    0.73
    Act Density 0.132%

    No Known Activations