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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research processes and criteria for selecting articles

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

    further actions or investigation

    np_acts-logits-general · gemini-2.0-flash

    further investigations or testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.56
     queſta
    -0.56
    ViewImports
    -0.53
    sizeCache
    -0.52
    LookAnd
    -0.52
    setupUi
    -0.51
    BASELINE
    -0.50
    AddTagHelper
    -0.50
     fusca
    -0.49
     Савезне
    -0.49
    POSITIVE LOGITS
     videre
    0.47
     further
    0.40
    进一步
    0.39
    Further
    0.38
     approfon
    0.37
    confirm
    0.35
     narrowed
    0.35
    indak
    0.35
    terung
    0.33
    further
    0.33
    Act Density 0.670%

    No Known Activations