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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references to figures or evidence in a document

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

    Numbers within sentences

    np_acts-logits-general · gemini-2.0-flash

    numbered citations or references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.67
    PhysRevLett
    -0.55
     <>",
    -0.49
    InitialState
    -0.49
    sstil
    -0.48
    печа
    -0.48
     betweenstory
    -0.47
    ValueStyle
    -0.47
     ist
    -0.47
     and
    -0.46
    POSITIVE LOGITS
     مرئيه
    0.81
     дописавши
    0.73
    ########.
    0.66
    findpost
    0.63
     فريبيس
    0.62
    BeginContext
    0.62
    يكب
    0.62
    CloseOperation
    0.61
    IsContent
    0.60
    awtextra
    0.58
    Act Density 0.055%

    No Known Activations