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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to research data or experimental outcomes

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

    numbers and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    めでとう
    -0.40
    enterOuterAlt
    -0.36
    .
    -0.35
    ret
    -0.35
    JsonFormat
    -0.35
     full
    -0.34
    las
    -0.33
     
    -0.33
    full
    -0.33
     Dubois
    -0.32
    POSITIVE LOGITS
    лтемелер
    0.63
    ſelf
    0.62
     queſta
    0.62
    istoitu
    0.60
    ſelves
    0.60
     zoude
    0.59
     henvisninger
    0.59
     jspb
    0.57
     houſe
    0.56
     leaſt
    0.55
    Act Density 0.363%

    No Known Activations