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

    Neuronpedia

    INDEX
    Explanations

    references to experimental procedures and conditions in scientific texts

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

    numerical values like "five", "ten", or amounts with "$" sign

    np_acts-logits-general · gemini-2.0-flash

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     almost
    -0.82
     незавершена
    -0.81
    脚注の使い方
    -0.80
     nine
    -0.80
     nearly
    -0.77
     ninth
    -0.76
    almost
    -0.74
     NINE
    -0.73
    ninth
    -0.73
     Almost
    -0.72
    POSITIVE LOGITS
    5
    0.92
     ten
    0.88
     Ten
    0.79
    Ten
    0.76
    ５
    0.70
    五十
    0.70
    ten
    0.66
     TEN
    0.66
     five
    0.65
    TEN
    0.64
    Act Density 0.647%

    No Known Activations