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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating previous discussions or references made by the author

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

    prior mentions

    np_acts-logits-general · gemini-2.0-flash

    referencing previous statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VolleyError
    -0.74
    GEBURTSDATUM
    -0.54
     FetchType
    -0.52
    NameInMap
    -0.49
    ::_('
    -0.47
     anstatt
    -0.47
    SharedCtor
    -0.45
    だそうです
    -0.45
    sic
    -0.42
     Voulez
    -0.42
    POSITIVE LOGITS
     earlier
    0.99
     previously
    0.92
    earlier
    0.87
    Earlier
    0.83
     previous
    0.80
     Earlier
    0.80
    Previously
    0.78
     thiệu
    0.77
     Previously
    0.75
     précédemment
    0.74
    Act Density 0.458%

    No Known Activations