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

    Neuronpedia

    INDEX
    Explanations

    elements related to HTTP headers and parameters in code snippets

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

    Code, configuration file, or technical terms

    np_acts-logits-general · gemini-2.0-flash

    getting configuration integer value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.59
     ligiloj
    -0.53
    crum
    -0.50
    Iden
    -0.47
    __':
    -0.47
     ihop
    -0.45
     Commencez
    -0.43
     gri
    -0.42
     yield
    -0.42
    __':
    -0.42
    POSITIVE LOGITS
     propOrder
    0.69
    ftagPool
    0.69
    addCriterion
    0.68
    NameInMap
    0.61
    帖最后由
    0.61
    mability
    0.57
    ibatis
    0.57
    openzeppelin
    0.57
    styleable
    0.57
    paksa
    0.56
    Act Density 0.420%

    No Known Activations