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

    Neuronpedia

    INDEX
    Explanations

    references to file names or identifiers within code snippets

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

    variable names and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.81
    AndEndTag
    -0.71
    IVEREF
    -0.62
    MemoryWarning
    -0.61
    RegressionTest
    -0.61
    ofire
    -0.58
     незавершена
    -0.57
    enterOuterAlt
    -0.57
    ')):
    -0.56
     comuniques
    -0.55
    POSITIVE LOGITS
     exist
    0.47
     existed
    0.45
     exists
    0.42
     tồn
    0.38
    exist
    0.36
    鲜
    0.35
    WindowListener
    0.35
    Exist
    0.35
     finnas
    0.35
     exis
    0.35
    Act Density 0.012%

    No Known Activations