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

    Neuronpedia

    INDEX
    Explanations

    the word "do", especially when capitalized within code

    oai_token-act-pair · gemini-2.0-flash

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Do
    -2.33
     Do
    -2.28
    do
    -2.28
     do
    -1.88
    DO
    -1.85
     DO
    -1.74
    <bos>
    -1.34
    dos
    -1.03
    Does
    -0.90
    does
    -0.89
    POSITIVE LOGITS
    IntoConstraints
    0.84
     NDEBUG
    0.63
    ruptedException
    0.62
     Efq
    0.61
     itſelf
    0.57
     contextLoads
    0.56
     שוליים
    0.56
     myſelf
    0.55
     Relaxed
    0.55
    makeText
    0.55
    Act Density 1.236%

    No Known Activations