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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks and their usage within the text

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

    Strings concatenated with spaces

    np_acts-logits-general · gemini-2.0-flash

    string concatenation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ../../
    -0.70
     transfieras
    -0.64
     Walkover
    -0.63
    )....
    -0.61
    ../../../
    -0.61
    Diwedd
    -0.60
    يكب
    -0.60
    Controllo
    -0.58
    ../
    -0.58
    freopen
    -0.57
    POSITIVE LOGITS
     StringTokenizer
    0.68
    ModelSerializer
    0.66
    createdDate
    0.62
    complexContent
    0.60
    coroutines
    0.58
    logenetic
    0.57
     "
    0.56
    philo
    0.56
    
    0.55
    bino
    0.55
    Act Density 0.140%

    No Known Activations