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

    Neuronpedia

    INDEX
    Explanations

    references to directories in code or file structures

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

    directories and installation paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Parcelable
    -0.44
     Pequ
    -0.42
    Expected
    -0.41
     Pasa
    -0.41
    kapan
    -0.41
     Manusia
    -0.40
    taine
    -0.40
    הם
    -0.40
    __":
    -0.40
    Unexpected
    -0.40
    POSITIVE LOGITS
    Dir
    2.14
     Dir
    1.77
    Dirs
    1.09
    dir
    1.04
    DIR
    1.00
     DIR
    0.88
    dirs
    0.87
     Directory
    0.82
     dirs
    0.79
     Directors
    0.78
    Act Density 0.008%

    No Known Activations