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

    Neuronpedia

    INDEX
    Explanations

    HTML and JavaScript elements in code

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

    Elements within brackets and parentheses

    np_acts-logits-general · gemini-2.0-flash

    gitbook references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MeasureSpec
    -0.40
     refroidissement
    -0.34
    useEffect
    -0.29
     alimentaria
    -0.26
    useState
    -0.26
    liğini
    -0.26
     CanadaChoose
    -0.25
    SuppressLint
    -0.25
     cadeira
    -0.25
     piemē
    -0.25
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.80
    <unused28>
    0.72
    <unused14>
    0.72
    [@BOS@]
    0.72
    <unused43>
    0.72
    <pad>
    0.72
    <unused23>
    0.72
    <unused41>
    0.72
    <unused3>
    0.71
    <unused8>
    0.71
    Act Density 0.181%

    No Known Activations