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

    Neuronpedia

    INDEX
    Explanations

    questions that begin with "Do"

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

    "Do" followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    do you and do not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ListTile
    -0.63
    Trichlor
    -0.59
    SpringBootTest
    -0.59
     Мексичка
    -0.59
     conting
    -0.58
     Crema
    -0.58
     integr
    -0.58
     Rebellion
    -0.57
     levis
    -0.57
    reversible
    -0.57
    POSITIVE LOGITS
     Do
    1.12
    Do
    1.11
     DO
    0.96
     do
    0.95
    DO
    0.86
    do
    0.85
    zdo
    0.78
    DoS
    0.66
     Dolan
    0.62
    penup
    0.62
    Act Density 0.095%

    No Known Activations