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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "mark" in various contexts, likely related to code or programming annotations

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

    mark command or adjective marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    googleapis
    -0.46
     functools
    -0.45
    nein
    -0.44
    syste
    -0.44
    ucchini
    -0.44
     :\
    -0.43
     userService
    -0.43
    bolic
    -0.42
    eeeeeeee
    -0.42
     Yoo
    -0.41
    POSITIVE LOGITS
    mark
    2.94
     mark
    2.66
    MARK
    2.42
    Mark
    2.41
     Mark
    2.33
     MARK
    2.25
    marks
    2.13
     marks
    1.98
    marking
    1.84
    Marks
    1.78
    Act Density 0.027%

    No Known Activations