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

    Neuronpedia

    INDEX
    Explanations

    references to the existence of files or directories in code or documentation

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

    checking for existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.58
    Gla
    -0.46
    الان
    -0.45
    UnusedPrivate
    -0.45
    JsonHelper
    -0.45
    Jal
    -0.45
    Jor
    -0.44
     SqlParameter
    -0.44
    Pri
    -0.42
     Julian
    -0.42
    POSITIVE LOGITS
    Exists
    2.41
     Exists
    1.51
    exists
    1.30
    EXISTS
    1.26
     EXISTS
    1.00
     exists
    0.92
    DoesNotExist
    0.85
    AlreadyExists
    0.80
    Existe
    0.72
    existe
    0.69
    Act Density 0.006%

    No Known Activations