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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating typical or expected conditions

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

    comparison of usual, expected, or normal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.54
    VYMaps
    -0.47
    henswürdigkeiten
    -0.47
    findpost
    -0.44
    wikidata
    -0.43
    ValueStyle
    -0.39
    сылкі
    -0.37
    tableFuture
    -0.37
    +#+#
    -0.36
    TagMode
    -0.36
    POSITIVE LOGITS
    Personendaten
    0.56
    isContained
    0.51
    unknownFields
    0.50
     esprits
    0.49
    webElement
    0.45
    InputBorder
    0.45
    reathable
    0.43
    erialized
    0.42
    iseite
    0.41
     autorytatywna
    0.41
    Act Density 0.031%

    No Known Activations