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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions related to numbers and ranks

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

    sequences of numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.66
     ModelExpression
    -0.62
     
    -0.61
     @"/
    -0.56
     صوتيه
    -0.54
    tanleria
    -0.54
     informée
    -0.51
    ंदीखरीदारी
    -0.49
    :✨
    -0.48
     CWE
    -0.48
    POSITIVE LOGITS
     sexuales
    0.40
     vectorielles
    0.39
    satunya
    0.39
    htë
    0.36
     dezelve
    0.36
     pazi
    0.36
    entityManager
    0.34
    unków
    0.34
     hmot
    0.34
     sexual
    0.34
    Act Density 0.033%

    No Known Activations