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

    Neuronpedia

    INDEX
    Explanations

    assertions and conclusions in various contexts

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

    comply / conform to reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.56
    AndEndTag
    -0.47
     дописавши
    -0.44
     createState
    -0.42
     оригіналу
    -0.41
     uğ
    -0.41
    IsMutable
    -0.40
    Cyfarwyddwr
    -0.39
    *****/
    -0.39
    Бахар
    -0.38
    POSITIVE LOGITS
    fillment
    0.52
     Trapp
    0.43
     comply
    0.40
    符合
    0.40
     Realität
    0.40
     вопло
    0.40
    現実
    0.39
     MaterialApp
    0.39
    Фак
    0.38
    compliant
    0.38
    Act Density 0.405%

    No Known Activations