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

    Neuronpedia

    INDEX
    Explanations

    interjections and question formats

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

    Text followed by questions

    np_acts-logits-general · gemini-2.0-flash

    questions starting with Q:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     معه
    -0.48
    herself
    -0.47
     Citizen
    -0.46
    arschijnlijk
    -0.46
     here
    -0.46
    ]=="
    -0.45
     سكانية
    -0.45
     herewith
    -0.44
    άσ
    -0.44
     Sorge
    -0.43
    POSITIVE LOGITS
    findpost
    0.92
     ModelExpression
    0.77
     saites
    0.70
    TestingModule
    0.70
    BeginContext
    0.68
    uxxxx
    0.66
    Geplaatst
    0.64
    ⓧ
    0.60
     تضيفلها
    0.59
    WebServlet
    0.58
    Act Density 0.095%

    No Known Activations