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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical values or percentages

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

    listing number 5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.62
    хьтан
    -0.62
    rayage
    -0.55
    XmlAccessType
    -0.54
    脚注の使い方
    -0.50
    忑
    -0.50
     ſoll
    -0.50
     Geiſt
    -0.49
     Taktlose
    -0.49
    SharedCtor
    -0.48
    POSITIVE LOGITS
    5
    0.63
     fifth
    0.56
     cinquième
    0.54
     Fifth
    0.52
     quinto
    0.52
    five
    0.50
    fifth
    0.49
    Fifth
    0.49
     sexto
    0.49
     sixth
    0.49
    Act Density 0.042%

    No Known Activations