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

    Neuronpedia

    INDEX
    Explanations

    terms related to efficiency and enhancement in various contexts

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

    Increase in a positive attribute

    np_acts-logits-general · gemini-2.0-flash

    increase or decrease in performance metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dirigez
    -0.45
     hieß
    -0.43
    uestamente
    -0.42
    accompag
    -0.41
     yazılı
    -0.41
    RequestMapping
    -0.40
    tyk
    -0.40
    tiche
    -0.40
     trenger
    -0.39
    Erreferentziak
    -0.39
    POSITIVE LOGITS
     productivity
    0.80
    TextHelper
    0.75
    WriteAttribute
    0.74
    ParallelGroup
    0.73
    AddHtmlAttribute
    0.72
     lenker
    0.72
    AddTagHelper
    0.71
     efficiency
    0.70
    Vidite
    0.69
    annica
    0.68
    Act Density 0.391%

    No Known Activations