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

    Neuronpedia

    INDEX
    Explanations

    elements related to structured data or JSON formats

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

    JSON-like structures with "name" and "cur" keys

    np_acts-logits-general · gemini-2.0-flash

    key-value pairs in structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThemeOverlay
    -0.49
    apiClient
    -0.47
    的作品
    -0.47
     урок
    -0.47
     {
    -0.46
     the
    -0.46
     U
    -0.46
     newVal
    -0.45
     -
    -0.44
     currentNode
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.89
    IsContent
    0.82
    enumii
    0.82
    __(/*!
    0.81
    UrlResolution
    0.81
     unknownFields
    0.79
    ​—
    0.76
    wikidata
    0.75
    enumi
    0.75
     Offisielt
    0.74
    Act Density 0.297%

    No Known Activations