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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms related to data analysis and experimental design

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

    allocations, assignments, and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.45
    HomeAsUpEnabled
    -0.42
    tagHelper
    -0.41
    bootstrapcdn
    -0.40
    AddTagHelper
    -0.40
    TAP
    -0.36
    classnames
    -0.35
     TAP
    -0.34
    tagHelperRunner
    -0.34
    truth
    -0.34
    POSITIVE LOGITS
    tanleria
    0.58
     Walkover
    0.54
    UAGE
    0.48
     allocations
    0.45
    RegressionTest
    0.44
     preferences
    0.44
    portál
    0.44
     refroidissement
    0.44
     zwey
    0.43
     honra
    0.43
    Act Density 0.081%

    No Known Activations