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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms, particularly those associated with backend development and data structures

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

    after underscores

    np_acts-logits-general · gemini-2.0-flash

    size parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.56
     Савезне
    -0.48
     мәкалә
    -0.42
     Italijani
    -0.40
    ]=>
    -0.39
    RegressionTest
    -0.37
     uLocal
    -0.37
    -0.37
    HasAnnotation
    -0.37
     Мексичка
    -0.36
    POSITIVE LOGITS
     autorytatywna
    0.58
     مرئيه
    0.50
    exitRule
    0.48
     identities
    0.46
    Datuak
    0.46
     defaultstate
    0.44
    Erreferentziak
    0.43
     availability
    0.43
     ddelwed
    0.43
    BagConstraints
    0.42
    Act Density 0.488%

    No Known Activations