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

    Neuronpedia

    INDEX
    Explanations

    words related to legality and citizenship

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gentes
    -0.57
    unce
    -0.46
    abt
    -0.44
    ing
    -0.44
    heed
    -0.42
    Referències
    -0.42
     따
    -0.42
    ekš
    -0.42
    VolleyError
    -0.41
     Carbon
    -0.40
    POSITIVE LOGITS
     legalized
    1.04
    Legal
    1.03
     lawful
    1.00
     légal
    0.99
    legal
    0.98
    lawful
    0.97
     legal
    0.96
     Legal
    0.94
     legality
    0.92
    出版年
    0.92
    Act Density 1.066%

    No Known Activations