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

    Neuronpedia

    INDEX
    Explanations

    language related to legal documents

    oai_token-act-pair · gemini-2.0-flash

    describing or mentioning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.72
    Datuak
    -0.71
    Hozzáférés
    -0.69
    Geplaatst
    -0.69
     Shakspeare
    -0.68
     Theſe
    -0.68
    UserScript
    -0.62
     الاطلاع
    -0.62
    RectangleBorder
    -0.59
    INSEE
    -0.59
    POSITIVE LOGITS
     mentions
    1.30
     mention
    1.29
     mentioning
    1.19
     describe
    1.16
     describes
    1.09
     describing
    1.04
     Mentions
    1.00
     stating
    0.96
    mention
    0.96
     Mention
    0.95
    Act Density 3.405%

    No Known Activations