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

    Neuronpedia

    INDEX
    Explanations

    running for office

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Close
    -0.07
    (review
    -0.07
     Linked
    -0.07
    כוכ
    -0.07
    算是
    -0.06
     Newsp
    -0.06
     suggestive
    -0.06
     เมษายน
    -0.06
     Egyptians
    -0.06
    _Al
    -0.06
    POSITIVE LOGITS
    Sab
    0.07
     Laundry
    0.07
    حقيقة
    0.06
    纷纷
    0.06
     sẻ
    0.06
    физ
    0.06
    とのこと
    0.06
     lim
    0.06
    命运
    0.06
     listener
    0.06
    Act Density 0.044%

    No Known Activations