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

    Neuronpedia

    INDEX
    Explanations

    references to programming methods and coding structures

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

    classic style code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.65
    󠁣
    -0.61
    AddTagHelper
    -0.58
    ItemBackground
    -0.57
    AsUp
    -0.57
     '\\;'
    -0.56
    +#+#
    -0.54
     otomatig
    -0.54
     AssemblyCulture
    -0.52
     للمعارف
    -0.52
    POSITIVE LOGITS
    Classic
    0.46
    classic
    0.44
    style
    0.44
    AVIS
    0.43
     dap
    0.42
     jos
    0.41
    Style
    0.41
     style
    0.41
     styles
    0.40
     modal
    0.40
    Act Density 0.000%

    No Known Activations