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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences or statements in the text

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

    decoding data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.50
     CanadaChoose
    -0.46
     فريبيس
    -0.40
    どうも
    -0.37
     AssemblyVersion
    -0.35
     AssemblyCompany
    -0.35
    Personensuche
    -0.34
     &___
    -0.34
    ValueStyle
    -0.33
    甚麼
    -0.33
    POSITIVE LOGITS
    PerformLayout
    0.49
    archi
    0.47
    ReusableCell
    0.44
    pośred
    0.43
    simmon
    0.42
    ("$.
    0.42
     useAppContext
    0.41
     gezond
    0.41
     trekken
    0.41
     houden
    0.41
    Act Density 0.360%

    No Known Activations