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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in text

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

    Code, quotes, or uncommon punctuation

    np_acts-logits-general · gemini-2.0-flash

    Q:, Data, News

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    élève
    -0.41
     rahasia
    -0.40
     umane
    -0.39
    以上に
    -0.39
     bekas
    -0.38
     parar
    -0.37
     escala
    -0.36
    VO
    -0.36
     ottenere
    -0.36
     haberse
    -0.36
    POSITIVE LOGITS
    awtextra
    0.94
    MLLoader
    0.87
    oredCriteria
    0.85
    TagMode
    0.81
     >=",
    0.81
    InjectAttribute
    0.81
    StoryboardSegue
    0.80
    setVerticalGroup
    0.80
    SerializedName
    0.80
    úgó
    0.73
    Act Density 0.012%

    No Known Activations