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

    Neuronpedia

    INDEX
    Explanations

    quantifiable quantities and descriptions in a variety of contexts

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

    quantifiers followed by abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jenn
    -0.39
     those
    -0.38
    ratulations
    -0.35
     Republicans
    -0.34
     restrictions
    -0.33
     constraints
    -0.33
     many
    -0.32
    Republicans
    -0.32
     standards
    -0.32
     những
    -0.32
    POSITIVE LOGITS
    httphttps
    0.84
     مرئيه
    0.84
    tanleria
    0.73
    таратура
    0.71
     BorderSide
    0.68
     المعيارى
    0.65
    ביוגרפיה
    0.60
    0.59
     Paglinawan
    0.58
     snippetHide
    0.55
    Act Density 0.123%

    No Known Activations