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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and factors

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

    prime factors and multiples of 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.70
     miniaturka
    -0.61
     ainfi
    -0.60
    archiwizowane
    -0.59
    ſelves
    -0.59
     incrí
    -0.59
     témoig
    -0.58
     contextLoads
    -0.57
    ſelf
    -0.57
     szcz
    -0.57
    POSITIVE LOGITS
    IANGLES
    0.57
    3
    0.56
     threefold
    0.40
    三
    0.39
    Trois
    0.39
     three
    0.38
    trois
    0.38
     III
    0.37
    Three
    0.37
    three
    0.36
    Act Density 0.327%

    No Known Activations