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

    Neuronpedia

    INDEX
    Explanations

    spaces between areas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manage
    -0.08
    ‌رس
    -0.06
     intelligent
    -0.06
    仅
    -0.06
     REMOVE
    -0.06
    以及
    -0.06
    เซอร
    -0.06
     Ryan
    -0.06
     Purple
    -0.06
     Rapid
    -0.06
    POSITIVE LOGITS
    (sz
    0.07
     उन
    0.06
     chall
    0.06
    ).[
    0.06
    �
    0.06
    监听页面
    0.06
    特別
    0.06
    totals
    0.06
    [:,
    0.06
     wow
    0.06
    Act Density 0.086%

    No Known Activations