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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate mathematical definitions or conditions involving variables and properties

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

    Followed by symbols: $, *

    np_acts-logits-general · gemini-2.0-flash

    all, any, every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Camar
    -0.51
    (&:
    -0.50
    DllImport
    -0.50
    出版年
    -0.49
    BorderFactory
    -0.47
    ByKey
    -0.46
     allude
    -0.46
    <()>
    -0.44
    )))));
    -0.44
    Stan
    -0.44
    POSITIVE LOGITS
    windowFixed
    0.90
     propOrder
    0.72
     sufficiently
    0.70
    帖最后由
    0.65
    :✨
    0.62
     belieb
    0.62
    HideFlags
    0.61
     pair
    0.60
     насељу
    0.60
     pairs
    0.59
    Act Density 0.989%

    No Known Activations