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

    Neuronpedia

    INDEX
    Explanations

    procedural and instructional content related to systems and features

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

    filed or listed under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Вікіпе
    -0.44
     moat
    -0.40
     Catawiki
    -0.40
     thiệu
    -0.39
    VolleyError
    -0.36
    scrapy
    -0.36
    plakat
    -0.34
    ʁ
    -0.34
    回戦
    -0.34
     Mojo
    -0.34
    POSITIVE LOGITS
     under
    2.25
    under
    1.77
    Under
    1.66
     bajo
    1.60
     unter
    1.59
     Under
    1.59
     onder
    1.44
     UNDER
    1.39
     تحت
    1.33
     sous
    1.30
    Act Density 0.125%

    No Known Activations