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

    Neuronpedia

    INDEX
    Explanations

    references to issued equipment or supplies

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

    after articles (a, the)

    np_acts-logits-general · gemini-2.0-flash

    Foreign words, Negroes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueGenerated
    -0.64
    ruvate
    -0.62
    脚注の使い方
    -0.58
    lapia
    -0.57
     microfiber
    -0.56
     arguably
    -0.56
    jestic
    -0.55
    pielt
    -0.55
    quatch
    -0.55
     Thankfully
    -0.54
    POSITIVE LOGITS
     ordinaire
    0.68
     thereto
    0.67
     groote
    0.64
     brano
    0.64
     therefrom
    0.63
     ordinaria
    0.63
     muß
    0.60
     Negroes
    0.60
     ordinaires
    0.59
     enfans
    0.59
    Act Density 0.646%

    No Known Activations