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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اط
    -0.06
    _Tab
    -0.06
    ιλο
    -0.06
     بنابر
    -0.06
     форму
    -0.06
    -utils
    -0.06
    errat
    -0.06
    考试
    -0.06
     affordable
    -0.06
    financial
    -0.06
    POSITIVE LOGITS
    ()<<
    0.06
     đủ
    0.06
     سم
    0.06
    眠
    0.06
    isodes
    0.06
     रह
    0.06
    WND
    0.06
     lễ
    0.06
     одна
    0.06
    	speed
    0.06
    Act Density 0.006%

    No Known Activations