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

    Neuronpedia

    INDEX
    Explanations

    words that appear in legal documents

    oai_token-act-pair · gemini-2.0-flash

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     P
    -0.56
    <eos>
    -0.45
     Sam
    -0.41
     N
    -0.41
    tec
    -0.40
     A
    -0.40
     Bar
    -0.40
     the
    -0.39
     
    -0.39
     a
    -0.38
    POSITIVE LOGITS
    featureID
    1.16
    DockStyle
    1.09
     الحره
    1.08
     للاسماء
    1.05
    CloseOperation
    1.05
    PreferredItem
    1.05
     дописавши
    1.05
     AssemblyProduct
    1.04
    principalColumn
    1.02
     חיצוניים
    1.00
    Act Density 0.987%

    No Known Activations