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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

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

    preceding a capital letter

    np_acts-logits-general · gemini-2.0-flash

    questions and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.95
    DoubleQuotes
    -0.74
     StatelessWidget
    -0.68
     CreateTagHelper
    -0.66
     podjela
    -0.65
     ***!
    -0.64
     ArrayAdapter
    -0.62
     AssemblyProduct
    -0.62
    StructEnd
    -0.62
    tagHelperRunner
    -0.62
    POSITIVE LOGITS
    kében
    0.54
    ┬
    0.54
    gebn
    0.50
     utafitiHapana
    0.49
    pédie
    0.49
    HORE
    0.48
    bezpe
    0.48
    LER
    0.47
     Davis
    0.47
    жели
    0.47
    Act Density 0.953%

    No Known Activations