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

    Neuronpedia

    INDEX
    Explanations

    patterns of formatting or structural elements within text

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

    Text preceding a section number

    np_acts-logits-general · gemini-2.0-flash

    English, foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.86
    OGND
    -0.86
     Италијани
    -0.81
    InvalidProtocol
    -0.79
    ########.
    -0.75
    sizeCache
    -0.71
    Personensuche
    -0.71
    Parcelize
    -0.71
     ویکی‌پدی
    -0.71
    (!__
    -0.70
    POSITIVE LOGITS
     tanong
    0.44
     entertained
    0.44
     ympä
    0.42
    Naissance
    0.41
     cue
    0.41
     näky
    0.40
    σιμοποι
    0.40
    langsung
    0.40
     palk
    0.39
    DeviceType
    0.39
    Act Density 0.033%

    No Known Activations