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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs and their relationships in data structures

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

    Key-value pairs or paired items

    np_acts-logits-general · gemini-2.0-flash

    pair or combo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     handleMessage
    -0.51
     trưng
    -0.47
    IsContent
    -0.45
     للاسماء
    -0.44
     allemaal
    -0.43
     صوتيه
    -0.43
    mopolitan
    -0.42
    umento
    -0.42
     HasFactory
    -0.42
    urahan
    -0.42
    POSITIVE LOGITS
     pair
    3.45
     pairs
    3.03
     Pair
    2.97
    pair
    2.95
    Pair
    2.77
     Pairs
    2.67
     PAIR
    2.65
     duo
    2.58
    pairs
    2.57
     pairing
    2.52
    Act Density 0.684%

    No Known Activations