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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate similarity or comparison

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

    connectors and relational words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.70
    ésultats
    -0.65
     חיצוניים
    -0.65
    лтемелер
    -0.64
     erſt
    -0.59
     témoig
    -0.58
     ſont
    -0.56
     beſte
    -0.56
    iſen
    -0.56
    onOptions
    -0.55
    POSITIVE LOGITS
    ronpa
    0.52
    izde
    0.33
     low
    0.33
    ngdoc
    0.31
     light
    0.30
     Hochsch
    0.30
    引
    0.30
    <h1>
    0.29
     lowland
    0.29
     preventing
    0.29
    Act Density 0.172%

    No Known Activations