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

    Neuronpedia

    INDEX
    Explanations

    references to directories or directory-related terms in code or documentation

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

    dir attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Knapp
    -0.57
     Pequ
    -0.53
    󠁮
    -0.53
    Kennedy
    -0.52
     HTMLElement
    -0.51
     Prest
    -0.51
     Salom
    -0.50
    稲田
    -0.50
    Maxim
    -0.50
    Nova
    -0.50
    POSITIVE LOGITS
     dir
    1.73
     Dir
    1.62
    dir
    1.49
    Dir
    1.43
     DIR
    1.34
    DIR
    1.21
     dirs
    1.10
     directory
    0.96
    dirs
    0.92
     Directory
    0.91
    Act Density 0.017%

    No Known Activations