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

    Neuronpedia

    INDEX
    Explanations

    consent and mental capacity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estad
    -0.08
     SUMMARY
    -0.07
    议事
    -0.07
     Hurricanes
    -0.07
    フランス
    -0.07
     chủ
    -0.07
    /connection
    -0.07
    텉
    -0.07
    ạm
    -0.07
    (userName
    -0.07
    POSITIVE LOGITS
    yster
    0.08
    _escape
    0.07
     quilt
    0.07
     disappears
    0.06
    webtoken
    0.06
    ⚰
    0.06
    拥抱
    0.06
    ={$
    0.06
    떻
    0.06
     FROM
    0.06
    Act Density 0.017%

    No Known Activations