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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating differences in quantities or measurements

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

    comparisons using greater than or less than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Портал
    -0.56
     المعيارى
    -0.55
    .*")]
    -0.48
    Orléans
    -0.45
    runt
    -0.44
    ffilm
    -0.44
    ்கள்
    -0.43
    葵
    -0.43
    goto
    -0.43
    AllAfrica
    -0.43
    POSITIVE LOGITS
    featureID
    0.54
     than
    0.53
    StoryboardSegue
    0.50
    LEncoder
    0.43
    ReusableCell
    0.41
     оригіналу
    0.40
     betweenstory
    0.40
    NOPQRST
    0.38
     BoxDecoration
    0.38
    ậc
    0.36
    Act Density 0.101%

    No Known Activations