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

    Neuronpedia

    INDEX
    Explanations

    references to users and their associated attributes

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

    Immediately preceding "interaction", "control", or "ID"

    np_acts-logits-general · gemini-2.0-flash

    user controls and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.72
     متعلقه
    -0.70
    IUrlHelper
    -0.68
    tagHelperRunner
    -0.67
    ########.
    -0.63
    WriteTagHelper
    -0.61
     rgba
    -0.60
    Diwedd
    -0.59
     AssemblyVersion
    -0.58
    setVerticalGroup
    -0.57
    POSITIVE LOGITS
     Defined
    0.76
    defined
    0.72
     defined
    0.71
    Defined
    0.69
    agent
    0.69
     friendly
    0.67
     agent
    0.62
     Agent
    0.58
     hjemme
    0.58
     Friendly
    0.58
    Act Density 0.051%

    No Known Activations